Class CU
Functionality up to CUDA version 3.2, which is the minimum version compatible with the LWJGL bindings, is guaranteed to be available. Functions introduced after CUDA 3.2 may or may not be missing, depending on the CUDA version available at runtime.
-
Nested Class Summary
Nested ClassesModifier and TypeClassDescriptionstatic final classContains the function pointers loaded from the NVCUDASharedLibrary. -
Field Summary
FieldsModifier and TypeFieldDescriptionstatic final intstatic final intstatic final intstatic final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intArray formats.static final intIndicates that the layered sparse CUDA array or CUDA mipmapped array has a single mip tail region for all layers.static final intSparse subresource types.static final intSparse subresource types.static final intCompute Modes.static final intCompute Modes.static final intCompute Modes.static final intContext creation flags.static final intContext creation flags.static final intContext creation flags.static final intContext creation flags.static final intContext creation flags.static final intContext creation flags.static final intContext creation flags.static final intContext creation flags.static final intContext creation flags.static final intArray indices for cube faces.static final intArray indices for cube faces.static final intArray indices for cube faces.static final intArray indices for cube faces.static final intArray indices for cube faces.static final intArray indices for cube faces.static final intEnum values:static final intEnum values:static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice properties.static final intDevice that represents the CPU.static final intDevice that represents an invalid device.static final intP2P Attributes.static final intP2P Attributes.static final intP2P Attributes.static final intP2P Attributes.static final intP2P Attributes.static final intEvent creation flags.static final intEvent creation flags.static final intEvent creation flags.static final intEvent creation flags.static final intEvent record flags.static final intEvent record flags.static final intEvent wait flags.static final intEvent wait flags.static final intExecution Affinity Typesstatic final intExecution Affinity Typesstatic final intExternal memory handle types.static final intExternal memory handle types.static final intExternal memory handle types.static final intExternal memory handle types.static final intExternal memory handle types.static final intExternal memory handle types.static final intExternal memory handle types.static final intExternal memory handle types.static final intExternal semaphore handle types.static final intExternal semaphore handle types.static final intExternal semaphore handle types.static final intExternal semaphore handle types.static final intExternal semaphore handle types.static final intExternal semaphore handle types.static final intExternal semaphore handle types.static final intExternal semaphore handle types.static final intExternal semaphore handle types.static final intExternal semaphore handle types.static final intBitmasks forDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS.static final intBitmasks forDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS.static final intThe targets forFlushGPUDirectRDMAWrites(CUflushGPUDirectRDMAWritesTarget)static final intThe scopes forFlushGPUDirectRDMAWrites(CUflushGPUDirectRDMAWritesScope)static final intThe scopes forFlushGPUDirectRDMAWrites(CUflushGPUDirectRDMAWritesScope)static final intFunction properties.static final intFunction properties.static final intFunction properties.static final intFunction properties.static final intFunction properties.static final intFunction properties.static final intFunction properties.static final intFunction properties.static final intFunction properties.static final intFunction properties.static final intFunction cache configurations.static final intFunction cache configurations.static final intFunction cache configurations.static final intFunction cache configurations.static final intFlags to specify search options.static final intFlags to specify search options.static final intFlags to specify search options.static final intPlatform native ordering for GPUDirect RDMA writes.static final intPlatform native ordering for GPUDirect RDMA writes.static final intPlatform native ordering for GPUDirect RDMA writes.static final intThe additional write options forGraphDebugDotPrint(CUgraphDebugDot_flags)static final intThe additional write options forGraphDebugDotPrint(CUgraphDebugDot_flags)static final intThe additional write options forGraphDebugDotPrint(CUgraphDebugDot_flags)static final intThe additional write options forGraphDebugDotPrint(CUgraphDebugDot_flags)static final intThe additional write options forGraphDebugDotPrint(CUgraphDebugDot_flags)static final intThe additional write options forGraphDebugDotPrint(CUgraphDebugDot_flags)static final intThe additional write options forGraphDebugDotPrint(CUgraphDebugDot_flags)static final intThe additional write options forGraphDebugDotPrint(CUgraphDebugDot_flags)static final intThe additional write options forGraphDebugDotPrint(CUgraphDebugDot_flags)static final intThe additional write options forGraphDebugDotPrint(CUgraphDebugDot_flags)static final intThe additional write options forGraphDebugDotPrint(CUgraphDebugDot_flags)static final intThe additional write options forGraphDebugDotPrint(CUgraphDebugDot_flags)static final intThe additional write options forGraphDebugDotPrint(CUgraphDebugDot_flags)static final intCUgraphExecUpdateResultstatic final intCUgraphExecUpdateResultstatic final intCUgraphExecUpdateResultstatic final intCUgraphExecUpdateResultstatic final intCUgraphExecUpdateResultstatic final intCUgraphExecUpdateResultstatic final intCUgraphExecUpdateResultstatic final intCUgraphExecUpdateResultstatic final intCUgraphMem_attributestatic final intCUgraphMem_attributestatic final intCUgraphMem_attributestatic final intCUgraphMem_attributestatic final intGraph node types.static final intGraph node types.static final intGraph node types.static final intGraph node types.static final intGraph node types.static final intGraph node types.static final intGraph node types.static final intGraph node types.static final intGraph node types.static final intGraph node types.static final intGraph node types.static final intGraph node types.static final intFlags for retaining user object references for graphs.static final intFlags for mapping and unmapping interop resources.static final intFlags for mapping and unmapping interop resources.static final intFlags for mapping and unmapping interop resources.static final intFlags to register a graphics resource.static final intFlags to register a graphics resource.static final intFlags to register a graphics resource.static final intFlags to register a graphics resource.static final intFlags to register a graphics resource.static final intstatic final intCUDA Ipc Mem Flags.static final intOnline compiler and linker options.static final intCaching modes fordlcm.static final intCaching modes fordlcm.static final intCaching modes fordlcm.static final intOnline compiler and linker options.static final intOnline compiler and linker options.static final intOnline compiler and linker options.static final intOnline compiler and linker options.static final intOnline compiler and linker options.static final intOnline compiler and linker options.static final intOnline compiler and linker options.static final intOnline compiler and linker options.static final intOnline compiler and linker options.static final intOnline compiler and linker options.static final intOnline compiler and linker options.static final intOnline compiler and linker options.static final intOnline compiler and linker options.static final intDevice code formats.static final intDevice code formats.static final intDevice code formats.static final intDevice code formats.static final intDevice code formats.static final intDevice code formats.static final intOnline compiler and linker options.static final intOnline compiler and linker options.static final intOnline compiler and linker options.static final intOnline compiler and linker options.static final intOnline compiler and linker options.static final intOnline compiler and linker options.static final intOnline compiler and linker options.static final intOnline compiler and linker options.static final intOnline compiler and linker options.static final intOnline compiler and linker options.static final intOnline compiler and linker options.static final intOnline compiler and linker options.static final intGraph kernel node Attributes (CUkernelNodeAttrID)static final intGraph kernel node Attributes (CUkernelNodeAttrID)static final longIndicator that the next value in theextraparameter toLaunchKernelwill be a pointer to a buffer containing all kernel parameters used for launching kernelf.static final longIndicator that the next value in theextraparameter toLaunchKernelwill be a pointer to asize_twhich contains the size of the buffer specified withLAUNCH_PARAM_BUFFER_POINTER.static final longEnd of array terminator for theextraparameter toLaunchKernel.static final intLimits.static final intLimits.static final intLimits.static final intLimits.static final intLimits.static final intLimits.static final intLimits.static final intSpecifies the memory protection flags for mapping.static final intSpecifies the memory protection flags for mapping.static final intSpecifies the memory protection flags for mapping.static final intMemory advise values.static final intMemory advise values.static final intMemory advise values.static final intMemory advise values.static final intMemory advise values.static final intMemory advise values.static final intFlag for requesting different optimal and required granularities for an allocation.static final intFlag for requesting different optimal and required granularities for an allocation.static final intSpecifies compression attribute for an allocation.static final intSpecifies compression attribute for an allocation.static final intDefines the allocation types available.static final intDefines the allocation types available.static final intCUDA Mem Attach Flags.static final intCUDA Mem Attach Flags.static final intCUDA Mem Attach Flags.static final intThis flag if set indicates that the memory will be used as a tile pool.static final intMemory handle types (CUmemHandleType)static final intFlags for specifying particular handle types.static final intFlags for specifying particular handle types.static final intFlags for specifying particular handle types.static final intFlags for specifying particular handle types.static final intSpecifies the type of location.static final intSpecifies the type of location.static final intMemory operation types.static final intMemory operation types.static final int(CUmem_range_attribute)static final int(CUmem_range_attribute)static final int(CUmem_range_attribute)static final int(CUmem_range_attribute)static final intFlags forMemHostAlloc.static final intFlags forMemHostAlloc.static final intFlags forMemHostAlloc.static final intFlags forMemHostRegister.static final intFlags forMemHostRegister.static final intFlags forMemHostRegister.static final intFlags forMemHostRegister.static final intMemory types.static final intMemory types.static final intMemory types.static final intMemory types.static final intCUDA memory pool attributes (CUmemPool_attribute)static final intCUDA memory pool attributes (CUmemPool_attribute)static final intCUDA memory pool attributes (CUmemPool_attribute)static final intCUDA memory pool attributes (CUmemPool_attribute)static final intCUDA memory pool attributes (CUmemPool_attribute)static final intCUDA memory pool attributes (CUmemPool_attribute)static final intCUDA memory pool attributes (CUmemPool_attribute)static final intCUDA memory pool attributes (CUmemPool_attribute)static final intOccupancy calculator flag.static final intOccupancy calculator flag.static final intFor texture references loaded into the module, use default texunit from texture reference.static final intAccess flags that specify the level of access the current context's device has on the memory referenced.static final intAccess flags that specify the level of access the current context's device has on the memory referenced.static final intAccess flags that specify the level of access the current context's device has on the memory referenced.static final intPointer information.static final intPointer information.static final intPointer information.static final intPointer information.static final intPointer information.static final intPointer information.static final intPointer information.static final intPointer information.static final intPointer information.static final intPointer information.static final intPointer information.static final intPointer information.static final intPointer information.static final intPointer information.static final intPointer information.static final intPointer information.static final intPointer information.static final intCubin matching fallback strategies.static final intCubin matching fallback strategies.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource view format.static final intResource types.static final intResource types.static final intResource types.static final intResource types.static final intShared memory configurations.static final intShared memory configurations.static final intShared memory configurations.static final intShared memory carveout configurations.static final intShared memory carveout configurations.static final intShared memory carveout configurations.static final intFlags forStreamUpdateCaptureDependencies).static final intStream Attributes (CUstreamAttrID)static final intStream Attributes (CUstreamAttrID)static final intPossible modes for stream capture thread interactions.static final intPossible modes for stream capture thread interactions.static final intPossible modes for stream capture thread interactions.static final intPossible stream capture statuses returned byStreamIsCapturing.static final intPossible stream capture statuses returned byStreamIsCapturing.static final intPossible stream capture statuses returned byStreamIsCapturing.static final intStream creation flags.static final longLegacy stream handle.static final intOperations forStreamBatchMemOp.static final intOperations forStreamBatchMemOp.static final intOperations forStreamBatchMemOp.static final intOperations forStreamBatchMemOp.static final intOperations forStreamBatchMemOp.static final intStream creation flags.static final longPer-thread stream handle.static final intFlags forStreamUpdateCaptureDependencies).static final intFlags forStreamWaitValue32andStreamWaitValue64.static final intFlags forStreamWaitValue32andStreamWaitValue64.static final intFlags forStreamWaitValue32andStreamWaitValue64.static final intFlags forStreamWaitValue32andStreamWaitValue64.static final intFlags forStreamWaitValue32andStreamWaitValue64.static final intFlags forStreamWriteValue32.static final intFlags forStreamWriteValue32.static final intCUsynchronizationPolicystatic final intCUsynchronizationPolicystatic final intCUsynchronizationPolicystatic final intCUsynchronizationPolicystatic final intOnline compilation targets.static final intOnline compilation targets.static final intOnline compilation targets.static final intOnline compilation targets.static final intOnline compilation targets.static final intOnline compilation targets.static final intOnline compilation targets.static final intOnline compilation targets.static final intOnline compilation targets.static final intOnline compilation targets.static final intOnline compilation targets.static final intOnline compilation targets.static final intOnline compilation targets.static final intOnline compilation targets.static final intOnline compilation targets.static final intOnline compilation targets.static final intOnline compilation targets.static final intTexture reference addressing modes.static final intTexture reference addressing modes.static final intTexture reference addressing modes.static final intTexture reference addressing modes.static final intTexture reference filtering modes.static final intTexture reference filtering modes.static final intFlag forTexRefSetArray.static final intFlag forTexRefSetFlags.static final intFlag forTexRefSetFlags.static final intFlag forTexRefSetFlags.static final intFlag forTexRefSetFlags.static final intFlags for user objects for graphs.static final intEnum values:static final intEnum values:static final intEnum values:static final intEnum values:static final intEnum values:static final intEnum values:static final intEnum values:static final intEnum values:static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intError codes.static final intIndicates that the external memory object is a dedicated resource.static final intWhen theflagsparameter ofCUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMScontains this flag, it indicates that signaling an external semaphore object should skip performing appropriate memory synchronization operations over all the external memory objects that are imported asEXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF, which otherwise are performed by default to ensure data coherency with other importers of the sameNvSciBufmemory objects.static final intWhen theflagsparameter ofCUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMScontains this flag, it indicates that waiting on an external semaphore object should skip performing appropriate memory synchronization operations over all the external memory objects that are imported asEXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF, which otherwise are performed by default to ensure data coherency with other importers of the sameNvSciBufmemory objects.static final intFlags for instantiating a graph.static final intWhenflagsofDeviceGetNvSciSyncAttributesis set to this, it indicates that application needs signaler specificNvSciSyncAttrto be filled bycuDeviceGetNvSciSyncAttributes.static final intWhenflagsofDeviceGetNvSciSyncAttributesis set to this, it indicates that application needs waiter specificNvSciSyncAttrto be filled bycuDeviceGetNvSciSyncAttributes.static final intError codes. -
Method Summary
Modifier and TypeMethodDescriptionstatic intcuArray3DCreate(PointerBuffer pHandle, CUDA_ARRAY3D_DESCRIPTOR pAllocateArray) Creates a 3D CUDA array.static intcuArray3DGetDescriptor(CUDA_ARRAY3D_DESCRIPTOR pArrayDescriptor, long hArray) Get a 3D CUDA array descriptor.static intcuArrayCreate(PointerBuffer pHandle, CUDA_ARRAY_DESCRIPTOR pAllocateArray) Creates a 1D or 2D CUDA array.static intcuArrayDestroy(long hArray) Destroys a CUDA array.static intcuArrayGetDescriptor(CUDA_ARRAY_DESCRIPTOR pArrayDescriptor, long hArray) Get a 1D or 2D CUDA array descriptor.static intcuArrayGetPlane(PointerBuffer pPlaneArray, long hArray, int planeIdx) Gets a CUDA array plane from a CUDA array.static intcuArrayGetSparseProperties(CUDA_ARRAY_SPARSE_PROPERTIES sparseProperties, long array) Returns the layout properties of a sparse CUDA array.static intcuCtxAttach(PointerBuffer pctx, int flags) Increment a context's usage-count.static intcuCtxCreate(PointerBuffer pctx, int flags, int dev) Create a CUDA context.static intcuCtxCreate_v3(PointerBuffer pctx, CUexecAffinityParam.Buffer paramsArray, int flags, int dev) Create a CUDA context with execution affinity.static intcuCtxDestroy(long ctx) Destroy a CUDA context.static intcuCtxDetach(long ctx) Decrement a context's usage-countstatic intcuCtxDisablePeerAccess(long peerContext) Disables direct access to memory allocations in a peer context and unregisters any registered allocations.static intcuCtxEnablePeerAccess(long peerContext, int Flags) Enables direct access to memory allocations in a peer context.static intcuCtxGetApiVersion(long ctx, IntBuffer version) Gets the context's API version.static intcuCtxGetCacheConfig(IntBuffer pconfig) Returns the preferred cache configuration for the current context.static intcuCtxGetCurrent(PointerBuffer pctx) Returns the CUDA context bound to the calling CPU thread.static intcuCtxGetDevice(IntBuffer device) Returns the device ID for the current context.static intcuCtxGetExecAffinity(CUexecAffinityParam.Buffer pExecAffinity, int type) Returns the execution affinity setting for the current context.static intcuCtxGetFlags(IntBuffer flags) Returns the flags for the current context.static intcuCtxGetLimit(PointerBuffer pvalue, int limit) Returns resource limits.static intcuCtxGetSharedMemConfig(IntBuffer pConfig) Returns the current shared memory configuration for the current context.static intcuCtxGetStreamPriorityRange(IntBuffer leastPriority, IntBuffer greatestPriority) Returns numerical values that correspond to the least and greatest stream priorities.static intcuCtxPopCurrent(PointerBuffer pctx) Pops the current CUDA context from the current CPU thread.static intcuCtxPushCurrent(long ctx) Pushes a context on the current CPU thread.static intResets all persisting lines in cache to normal status.static intcuCtxSetCacheConfig(int config) Sets the preferred cache configuration for the current context.static intcuCtxSetCurrent(long ctx) Binds the specified CUDA context to the calling CPU thread.static intcuCtxSetLimit(int limit, long value) Set resource limits.static intcuCtxSetSharedMemConfig(int config) Sets the shared memory configuration for the current context.static intBlock for a context's tasks to complete.static intcuDestroyExternalMemory(long extMem) Destroys an external memory object.static intcuDestroyExternalSemaphore(long extSem) Destroys an external semaphore.static intcuDeviceCanAccessPeer(IntBuffer canAccessPeer, int dev, int peerDev) Queries if a device may directly access a peer device's memory.static intcuDeviceComputeCapability(IntBuffer major, IntBuffer minor, int dev) Returns the compute capability of the device.static intcuDeviceGet(IntBuffer device, int ordinal) Returns a handle to a compute device.static intcuDeviceGetAttribute(IntBuffer pi, int attrib, int dev) Returns information about the device.static intcuDeviceGetByPCIBusId(IntBuffer dev, CharSequence pciBusId) Returns a handle to a compute device.static intcuDeviceGetByPCIBusId(IntBuffer dev, ByteBuffer pciBusId) Returns a handle to a compute device.static intcuDeviceGetCount(IntBuffer count) Returns the number of compute-capable devices.static intcuDeviceGetDefaultMemPool(PointerBuffer pool_out, int dev) Returns the default mempool of a device.static intcuDeviceGetExecAffinitySupport(IntBuffer pi, int type, int dev) Returns information about the execution affinity support of the device.static intcuDeviceGetGraphMemAttribute(int device, int attr, ByteBuffer value) Query asynchronous allocation attributes related to graphs.static intcuDeviceGetGraphMemAttribute(int device, int attr, LongBuffer value) Query asynchronous allocation attributes related to graphs.static intcuDeviceGetLuid(ByteBuffer luid, IntBuffer deviceNodeMask, int dev) Return an LUID and device node mask for the devicestatic intcuDeviceGetMemPool(PointerBuffer pool, int dev) Gets the current mempool for a device.static intcuDeviceGetName(ByteBuffer name, int dev) Returns an identifer string for the device.static intcuDeviceGetNvSciSyncAttributes(ByteBuffer nvSciSyncAttrList, int dev, int flags) ReturnNvSciSyncattributes that this device can support.static intcuDeviceGetP2PAttribute(IntBuffer value, int attrib, int srcDevice, int dstDevice) Queries attributes of the link between two devices.static intcuDeviceGetPCIBusId(ByteBuffer pciBusId, int dev) Returns a PCI Bus Id string for the device.static intcuDeviceGetProperties(CUdevprop prop, int dev) Returns properties for a selected device.static intcuDeviceGetTexture1DLinearMaxWidth(PointerBuffer maxWidthInElements, int format, int numChannels, int dev) Returns the maximum number of elements allocatable in a 1D linear texture for a given texture element size.static intcuDeviceGetUuid(CUuuid uuid, int dev) Return an UUID for the device.static intcuDeviceGetUuid_v2(CUuuid uuid, int dev) Return an UUID for the device (11.4+).static intcuDeviceGraphMemTrim(int device) Free unused memory that was cached on the specified device for use with graphs back to the OS.static intcuDevicePrimaryCtxGetState(int dev, IntBuffer flags, IntBuffer active) Get the state of the primary context.static intcuDevicePrimaryCtxRelease(int dev) Release the primary context on the GPU.static intcuDevicePrimaryCtxReset(int dev) Destroy all allocations and reset all state on the primary context.static intcuDevicePrimaryCtxRetain(PointerBuffer pctx, int dev) Retain the primary context on the GPU.static intcuDevicePrimaryCtxSetFlags(int dev, int flags) Set flags for the primary context.static intcuDeviceSetGraphMemAttribute(int device, int attr, ByteBuffer value) Set asynchronous allocation attributes related to graphs.static intcuDeviceSetGraphMemAttribute(int device, int attr, LongBuffer value) Set asynchronous allocation attributes related to graphs.static intcuDeviceSetMemPool(int dev, long pool) Sets the current memory pool of a devicestatic intcuDeviceTotalMem(PointerBuffer bytes, int dev) Returns the total amount of memory on the devicestatic intcuDriverGetVersion(IntBuffer driverVersion) Returns the latest CUDA version supported by driver.static intcuEventCreate(PointerBuffer phEvent, int Flags) Creates an event.static intcuEventDestroy(long hEvent) Destroys an event.static intcuEventElapsedTime(FloatBuffer pMilliseconds, long hStart, long hEnd) Computes the elapsed time between two events.static intcuEventQuery(long hEvent) Queries an event's status.static intcuEventRecord(long hEvent, long hStream) Records an event.static intcuEventRecordWithFlags(long hEvent, long hStream, int flags) Records an event.static intcuEventSynchronize(long hEvent) Waits for an event to complete.static intcuExternalMemoryGetMappedBuffer(PointerBuffer devPtr, long extMem, CUDA_EXTERNAL_MEMORY_BUFFER_DESC bufferDesc) Maps a buffer onto an imported memory object.static intcuExternalMemoryGetMappedMipmappedArray(PointerBuffer mipmap, long extMem, CUDA_EXTERNAL_MEMORY_MIPMAPPED_ARRAY_DESC mipmapDesc) Maps a CUDA mipmapped array onto an external memory object.static intcuFlushGPUDirectRDMAWrites(int target, int scope) Blocks until remote writes are visible to the specified scope.static intcuFuncGetAttribute(IntBuffer pi, int attrib, long hfunc) Returns information about a function.static intcuFuncGetModule(PointerBuffer hmod, long hfunc) Returns a module handle.static intcuFuncSetAttribute(long hfunc, int attrib, int value) Sets information about a function.static intcuFuncSetBlockShape(long hfunc, int x, int y, int z) Sets the block-dimensions for the function.static intcuFuncSetCacheConfig(long hfunc, int config) Sets the preferred cache configuration for a device function.static intcuFuncSetSharedMemConfig(long hfunc, int config) Sets the shared memory configuration for a device function.static intcuFuncSetSharedSize(long hfunc, int bytes) Sets the dynamic shared-memory size for the function.static intcuGetErrorName(int error, PointerBuffer pStr) Gets the string representation of an error code enum name.static intcuGetErrorString(int error, PointerBuffer pStr) Gets the string description of an error code.static intcuGetExportTable(PointerBuffer ppExportTable, CUuuid pExportTableId) static intcuGetProcAddress(CharSequence symbol, PointerBuffer pfn, int cudaVersion, long flags) Returns the requested driver API function pointer.static intcuGetProcAddress(ByteBuffer symbol, PointerBuffer pfn, int cudaVersion, long flags) Returns the requested driver API function pointer.static intcuGraphAddChildGraphNode(PointerBuffer phGraphNode, long hGraph, PointerBuffer dependencies, long childGraph) Creates a child graph node and adds it to a graph.static intcuGraphAddDependencies(long hGraph, PointerBuffer from, PointerBuffer to) Adds dependency edges to a graph.static intcuGraphAddEmptyNode(PointerBuffer phGraphNode, long hGraph, PointerBuffer dependencies) Creates an empty node and adds it to a graph.static intcuGraphAddEventRecordNode(PointerBuffer phGraphNode, long hGraph, PointerBuffer dependencies, long event) Creates an event record node and adds it to a graph.static intcuGraphAddEventWaitNode(PointerBuffer phGraphNode, long hGraph, PointerBuffer dependencies, long event) Creates an event wait node and adds it to a graph.static intcuGraphAddExternalSemaphoresSignalNode(PointerBuffer phGraphNode, long hGraph, PointerBuffer dependencies, CUDA_EXT_SEM_SIGNAL_NODE_PARAMS nodeParams) Creates an external semaphore signal node and adds it to a graph.static intcuGraphAddExternalSemaphoresWaitNode(PointerBuffer phGraphNode, long hGraph, PointerBuffer dependencies, CUDA_EXT_SEM_WAIT_NODE_PARAMS nodeParams) Creates an external semaphore wait node and adds it to a graph.static intcuGraphAddHostNode(PointerBuffer phGraphNode, long hGraph, PointerBuffer dependencies, CUDA_HOST_NODE_PARAMS nodeParams) Creates a host execution node and adds it to a graph.static intcuGraphAddKernelNode(PointerBuffer phGraphNode, long hGraph, PointerBuffer dependencies, CUDA_KERNEL_NODE_PARAMS nodeParams) Creates a kernel execution node and adds it to a graph.static intcuGraphAddMemAllocNode(PointerBuffer phGraphNode, long hGraph, PointerBuffer dependencies, CUDA_MEM_ALLOC_NODE_PARAMS nodeParams) Creates an allocation node and adds it to a graph.static intcuGraphAddMemcpyNode(PointerBuffer phGraphNode, long hGraph, PointerBuffer dependencies, CUDA_MEMCPY3D copyParams, long ctx) Creates a memcpy node and adds it to a graph.static intcuGraphAddMemFreeNode(PointerBuffer phGraphNode, long hGraph, PointerBuffer dependencies, long dptr) Creates a memory free node and adds it to a graph.static intcuGraphAddMemsetNode(PointerBuffer phGraphNode, long hGraph, PointerBuffer dependencies, CUDA_MEMSET_NODE_PARAMS memsetParams, long ctx) Creates a memset node and adds it to a graph.static intcuGraphChildGraphNodeGetGraph(long hNode, PointerBuffer phGraph) Gets a handle to the embedded graph of a child graph node.static intcuGraphClone(PointerBuffer phGraphClone, long originalGraph) Clones a graph.static intcuGraphCreate(PointerBuffer phGraph, int flags) Creates a graph.static intcuGraphDebugDotPrint(long hGraph, CharSequence path, int flags) Write a DOT file describing graph structure.static intcuGraphDebugDotPrint(long hGraph, ByteBuffer path, int flags) Write a DOT file describing graph structure.static intcuGraphDestroy(long hGraph) Destroys a graph.static intcuGraphDestroyNode(long hNode) Remove a node from the graph.static intcuGraphEventRecordNodeGetEvent(long hNode, PointerBuffer event_out) Returns the event associated with an event record node.static intcuGraphEventRecordNodeSetEvent(long hNode, long event) Sets an event record node's event.static intcuGraphEventWaitNodeGetEvent(long hNode, PointerBuffer event_out) Returns the event associated with an event wait node.static intcuGraphEventWaitNodeSetEvent(long hNode, long event) Sets an event wait node's event.static intcuGraphExecChildGraphNodeSetParams(long hGraphExec, long hNode, long childGraph) Updates node parameters in the child graph node in the givengraphExec.static intcuGraphExecDestroy(long hGraphExec) Destroys an executable graph.static intcuGraphExecEventRecordNodeSetEvent(long hGraphExec, long hNode, long event) Sets the event for an event record node in the givengraphExec.static intcuGraphExecEventWaitNodeSetEvent(long hGraphExec, long hNode, long event) Sets the event for an event wait node in the givengraphExec.static intcuGraphExecExternalSemaphoresSignalNodeSetParams(long hGraphExec, long hNode, CUDA_EXT_SEM_SIGNAL_NODE_PARAMS nodeParams) Sets the parameters for an external semaphore signal node in the givengraphExec.static intcuGraphExecExternalSemaphoresWaitNodeSetParams(long hGraphExec, long hNode, CUDA_EXT_SEM_WAIT_NODE_PARAMS nodeParams) Sets the parameters for an external semaphore wait node in the given graphExec.static intcuGraphExecHostNodeSetParams(long hGraphExec, long hNode, CUDA_HOST_NODE_PARAMS nodeParams) Sets the parameters for a host node in the givengraphExec.static intcuGraphExecKernelNodeSetParams(long hGraphExec, long hNode, CUDA_KERNEL_NODE_PARAMS nodeParams) Sets the parameters for a kernel node in the givengraphExec.static intcuGraphExecMemcpyNodeSetParams(long hGraphExec, long hNode, CUDA_MEMCPY3D copyParams, long ctx) Sets the parameters for a memcpy node in the givengraphExec.static intcuGraphExecMemsetNodeSetParams(long hGraphExec, long hNode, CUDA_MEMSET_NODE_PARAMS memsetParams, long ctx) Sets the parameters for amemsetnode in the givengraphExec.static intcuGraphExecUpdate(long hGraphExec, long hGraph, PointerBuffer hErrorNode_out, IntBuffer updateResult_out) Check whether an executable graph can be updated with a graph and perform the update if possible.static intcuGraphExternalSemaphoresSignalNodeGetParams(long hNode, CUDA_EXT_SEM_SIGNAL_NODE_PARAMS params_out) Returns an external semaphore signal node's parameters.static intcuGraphExternalSemaphoresSignalNodeSetParams(long hNode, CUDA_EXT_SEM_SIGNAL_NODE_PARAMS nodeParams) Sets an external semaphore signal node's parameters.static intcuGraphExternalSemaphoresWaitNodeGetParams(long hNode, CUDA_EXT_SEM_WAIT_NODE_PARAMS params_out) Returns an external semaphore wait node's parameters.static intcuGraphExternalSemaphoresWaitNodeSetParams(long hNode, CUDA_EXT_SEM_WAIT_NODE_PARAMS nodeParams) Sets an external semaphore wait node's parameters.static intcuGraphGetEdges(long hGraph, PointerBuffer from, PointerBuffer to, PointerBuffer numEdges) Returns a graph's dependency edges.static intcuGraphGetNodes(long hGraph, PointerBuffer nodes, PointerBuffer numNodes) Returns a graph's nodes.static intcuGraphGetRootNodes(long hGraph, PointerBuffer rootNodes, PointerBuffer numRootNodes) Returns a graph's root nodes.static intcuGraphHostNodeGetParams(long hNode, CUDA_HOST_NODE_PARAMS nodeParams) Returns a host node's parameters.static intcuGraphHostNodeSetParams(long hNode, CUDA_HOST_NODE_PARAMS nodeParams) Sets a host node's parameters.static intcuGraphicsMapResources(PointerBuffer resources, long hStream) Map graphics resources for access by CUDA.static intcuGraphicsResourceGetMappedMipmappedArray(PointerBuffer pMipmappedArray, long resource) Get a mipmapped array through which to access a mapped graphics resource.static intcuGraphicsResourceGetMappedPointer(PointerBuffer pDevPtr, PointerBuffer pSize, long resource) Get a device pointer through which to access a mapped graphics resource.static intcuGraphicsResourceSetMapFlags(long resource, int flags) Set usage flags for mapping a graphics resource.static intcuGraphicsSubResourceGetMappedArray(PointerBuffer pArray, long resource, int arrayIndex, int mipLevel) Get an array through which to access a subresource of a mapped graphics resource.static intcuGraphicsUnmapResources(PointerBuffer resources, long hStream) Unmap graphics resources.static intcuGraphicsUnregisterResource(long resource) Unregisters a graphics resource for access by CUDA.static intcuGraphInstantiate(PointerBuffer phGraphExec, long hGraph, PointerBuffer phErrorNode, ByteBuffer logBuffer) Creates an executable graph from a graph.static intcuGraphInstantiateWithFlags(PointerBuffer phGraphExec, long hGraph, long flags) Creates an executable graph from a graph.static intcuGraphKernelNodeCopyAttributes(long dst, long src) Copies attributes from source node to destination node.static intcuGraphKernelNodeGetAttribute(long hNode, int attr, CUkernelNodeAttrValue value_out) Queries node attribute.static intcuGraphKernelNodeGetParams(long hNode, CUDA_KERNEL_NODE_PARAMS nodeParams) Returns a kernel node's parameters.static intcuGraphKernelNodeSetAttribute(long hNode, int attr, CUkernelNodeAttrValue value) Sets node attribute.static intcuGraphKernelNodeSetParams(long hNode, CUDA_KERNEL_NODE_PARAMS nodeParams) Sets a kernel node's parameters.static intcuGraphLaunch(long hGraphExec, long hStream) Launches an executable graph in a stream.static intcuGraphMemAllocNodeGetParams(long hNode, CUDA_MEM_ALLOC_NODE_PARAMS params_out) Returns a memory alloc node's parameters.static intcuGraphMemcpyNodeGetParams(long hNode, CUDA_MEMCPY3D nodeParams) Returns a memcpy node's parameters.static intcuGraphMemcpyNodeSetParams(long hNode, CUDA_MEMCPY3D nodeParams) Sets a memcpy node's parameters.static intcuGraphMemFreeNodeGetParams(long hNode, PointerBuffer dptr_out) Returns a memory free node's parameters.static intcuGraphMemsetNodeGetParams(long hNode, CUDA_MEMSET_NODE_PARAMS nodeParams) Returns a memset node's parameters.static intcuGraphMemsetNodeSetParams(long hNode, CUDA_MEMSET_NODE_PARAMS nodeParams) Sets a memset node's parameters.static intcuGraphNodeFindInClone(PointerBuffer phNode, long hOriginalNode, long hClonedGraph) Finds a cloned version of a node.static intcuGraphNodeGetDependencies(long hNode, PointerBuffer dependencies, PointerBuffer numDependencies) Returns a node's dependencies.static intcuGraphNodeGetDependentNodes(long hNode, PointerBuffer dependentNodes, PointerBuffer numDependentNodes) Returns a node's dependent nodes.static intcuGraphNodeGetType(long hNode, IntBuffer type) Returns a node's type.static intcuGraphReleaseUserObject(long graph, long object, int count) Release a user object reference from a graph.static intcuGraphRemoveDependencies(long hGraph, PointerBuffer from, PointerBuffer to) Removes dependency edges from a graph.static intcuGraphRetainUserObject(long graph, long object, int count, int flags) Retain a reference to a user object from a graph.static intcuGraphUpload(long hGraphExec, long hStream) Uploads an executable graph in a stream.static intcuImportExternalMemory(PointerBuffer extMem_out, CUDA_EXTERNAL_MEMORY_HANDLE_DESC memHandleDesc) Imports an external memory object.static intcuImportExternalSemaphore(PointerBuffer extSem_out, CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC semHandleDesc) Imports an external semaphore.static intcuInit(int Flags) Initialize the CUDA driver API.static intcuIpcCloseMemHandle(long dptr) Attempts to close memory mapped withIpcOpenMemHandle.static intcuIpcGetEventHandle(CUIPCEventHandle pHandle, long event) Gets an interprocess handle for a previously allocated event.static intcuIpcGetMemHandle(CUIPCMemHandle pHandle, long dptr) Gets an interprocess memory handle for an existing device memory allocation.static intcuIpcOpenEventHandle(PointerBuffer phEvent, CUIPCEventHandle handle) Opens an interprocess event handle for use in the current process.static intcuIpcOpenMemHandle(PointerBuffer pdptr, CUIPCMemHandle handle, int Flags) Opens an interprocess memory handle exported from another process and returns a device pointer usable in the local process.static intcuLaunch(long f) Launches a CUDA function.static intcuLaunchCooperativeKernel(long f, int gridDimX, int gridDimY, int gridDimZ, int blockDimX, int blockDimY, int blockDimZ, int sharedMemBytes, long hStream, PointerBuffer kernelParams) Launches a CUDA function where thread blocks can cooperate and synchronize as they execute.static intcuLaunchCooperativeKernelMultiDevice(CUDA_LAUNCH_PARAMS.Buffer launchParamsList, int flags) Launches CUDA functions on multiple devices where thread blocks can cooperate and synchronize as they executeDeprecated: This function is deprecated as of CUDA 11.3.static intcuLaunchGrid(long f, int grid_width, int grid_height) Launches a CUDA function.static intcuLaunchGridAsync(long f, int grid_width, int grid_height, long hStream) Launches a CUDA function.static intcuLaunchHostFunc(long hStream, CUhostFnI fn, long userData) Enqueues a host function call in a stream.static intcuLaunchKernel(long f, int gridDimX, int gridDimY, int gridDimZ, int blockDimX, int blockDimY, int blockDimZ, int sharedMemBytes, long hStream, PointerBuffer kernelParams, PointerBuffer extra) Launches a CUDA function.static intcuLinkAddData(long state, int type, ByteBuffer data, CharSequence name, IntBuffer options, PointerBuffer optionValues) Add an input to a pending linker invocation.static intcuLinkAddData(long state, int type, ByteBuffer data, ByteBuffer name, IntBuffer options, PointerBuffer optionValues) Add an input to a pending linker invocation.static intcuLinkAddFile(long state, int type, CharSequence path, IntBuffer options, PointerBuffer optionValues) Add a file input to a pending linker invocation.static intcuLinkAddFile(long state, int type, ByteBuffer path, IntBuffer options, PointerBuffer optionValues) Add a file input to a pending linker invocation.static intcuLinkComplete(long state, PointerBuffer cubinOut, PointerBuffer sizeOut) Complete a pending linker invocation.static intcuLinkCreate(IntBuffer options, PointerBuffer optionValues, PointerBuffer stateOut) Creates a pending JIT linker invocation.static intcuLinkDestroy(long state) Destroys state for a JIT linker invocation.static intcuMemAddressFree(long ptr, long size) Free an address range reservation.static intcuMemAddressReserve(PointerBuffer ptr, long size, long alignment, long addr, long flags) Allocate an address range reservation.static intcuMemAdvise(long devPtr, long count, int advice, int device) Advise about the usage of a given memory range.static intcuMemAlloc(PointerBuffer dptr, long bytesize) Allocates device memory.static intcuMemAllocAsync(PointerBuffer dptr, long bytesize, long hStream) Allocates memory with stream ordered semanticsstatic intcuMemAllocFromPoolAsync(PointerBuffer dptr, long bytesize, long pool, long hStream) Allocates memory from a specified pool with stream ordered semantics.static intcuMemAllocHost(PointerBuffer pp, long bytesize) Allocates page-locked host memory.static intcuMemAllocManaged(PointerBuffer dptr, long bytesize, int flags) Allocates memory that will be automatically managed by the Unified Memory system.static intcuMemAllocPitch(PointerBuffer dptr, PointerBuffer pPitch, long WidthInBytes, long Height, int ElementSizeBytes) Allocates pitched device memory.static intcuMemcpy(long dst, long src, long ByteCount) Copies memory.static intcuMemcpy2D(CUDA_MEMCPY2D pCopy) Copies memory for 2D arrays.static intcuMemcpy2DAsync(CUDA_MEMCPY2D pCopy, long hStream) Copies memory for 2D arrays.static intcuMemcpy2DUnaligned(CUDA_MEMCPY2D pCopy) Copies memory for 2D arrays.static intcuMemcpy3D(CUDA_MEMCPY3D pCopy) Copies memory for 3D arrays.static intcuMemcpy3DAsync(CUDA_MEMCPY3D pCopy, long hStream) Copies memory for 3D arrays.static intcuMemcpy3DPeer(CUDA_MEMCPY3D_PEER pCopy) Copies memory between contexts.static intcuMemcpy3DPeerAsync(CUDA_MEMCPY3D_PEER pCopy, long hStream) Copies memory between contexts asynchronously.static intcuMemcpyAsync(long dst, long src, long ByteCount, long hStream) Copies memory asynchronously.static intcuMemcpyAtoA(long dstArray, long dstOffset, long srcArray, long srcOffset, long ByteCount) Copies memory from Array to Array.static intcuMemcpyAtoD(long dstDevice, long srcArray, long srcOffset, long ByteCount) Copies memory from Array to Device.static intcuMemcpyAtoH(ByteBuffer dstHost, long srcArray, long srcOffset) Copies memory from Array to Host.static intcuMemcpyAtoH(DoubleBuffer dstHost, long srcArray, long srcOffset) Copies memory from Array to Host.static intcuMemcpyAtoH(FloatBuffer dstHost, long srcArray, long srcOffset) Copies memory from Array to Host.static intcuMemcpyAtoH(IntBuffer dstHost, long srcArray, long srcOffset) Copies memory from Array to Host.static intcuMemcpyAtoH(LongBuffer dstHost, long srcArray, long srcOffset) Copies memory from Array to Host.static intcuMemcpyAtoH(ShortBuffer dstHost, long srcArray, long srcOffset) Copies memory from Array to Host.static intcuMemcpyAtoH(PointerBuffer dstHost, long srcArray, long srcOffset) Copies memory from Array to Host.static intcuMemcpyAtoHAsync(ByteBuffer dstHost, long srcArray, long srcOffset, long hStream) Copies memory from Array to Host.static intcuMemcpyAtoHAsync(DoubleBuffer dstHost, long srcArray, long srcOffset, long hStream) Copies memory from Array to Host.static intcuMemcpyAtoHAsync(FloatBuffer dstHost, long srcArray, long srcOffset, long hStream) Copies memory from Array to Host.static intcuMemcpyAtoHAsync(IntBuffer dstHost, long srcArray, long srcOffset, long hStream) Copies memory from Array to Host.static intcuMemcpyAtoHAsync(LongBuffer dstHost, long srcArray, long srcOffset, long hStream) Copies memory from Array to Host.static intcuMemcpyAtoHAsync(ShortBuffer dstHost, long srcArray, long srcOffset, long hStream) Copies memory from Array to Host.static intcuMemcpyAtoHAsync(PointerBuffer dstHost, long srcArray, long srcOffset, long hStream) Copies memory from Array to Host.static intcuMemcpyDtoA(long dstArray, long dstOffset, long srcDevice, long ByteCount) Copies memory from Device to Array.static intcuMemcpyDtoD(long dstDevice, long srcDevice, long ByteCount) Copies memory from Device to Device.static intcuMemcpyDtoDAsync(long dstDevice, long srcDevice, long ByteCount, long hStream) Copies memory from Device to Device.static intcuMemcpyDtoH(ByteBuffer dstHost, long srcDevice) Copies memory from Device to Host.static intcuMemcpyDtoH(DoubleBuffer dstHost, long srcDevice) Copies memory from Device to Host.static intcuMemcpyDtoH(FloatBuffer dstHost, long srcDevice) Copies memory from Device to Host.static intcuMemcpyDtoH(IntBuffer dstHost, long srcDevice) Copies memory from Device to Host.static intcuMemcpyDtoH(LongBuffer dstHost, long srcDevice) Copies memory from Device to Host.static intcuMemcpyDtoH(ShortBuffer dstHost, long srcDevice) Copies memory from Device to Host.static intcuMemcpyDtoH(PointerBuffer dstHost, long srcDevice) Copies memory from Device to Host.static intcuMemcpyDtoHAsync(ByteBuffer dstHost, long srcDevice, long hStream) Copies memory from Device to Host.static intcuMemcpyDtoHAsync(DoubleBuffer dstHost, long srcDevice, long hStream) Copies memory from Device to Host.static intcuMemcpyDtoHAsync(FloatBuffer dstHost, long srcDevice, long hStream) Copies memory from Device to Host.static intcuMemcpyDtoHAsync(IntBuffer dstHost, long srcDevice, long hStream) Copies memory from Device to Host.static intcuMemcpyDtoHAsync(LongBuffer dstHost, long srcDevice, long hStream) Copies memory from Device to Host.static intcuMemcpyDtoHAsync(ShortBuffer dstHost, long srcDevice, long hStream) Copies memory from Device to Host.static intcuMemcpyDtoHAsync(PointerBuffer dstHost, long srcDevice, long hStream) Copies memory from Device to Host.static intcuMemcpyHtoA(long dstArray, long dstOffset, ByteBuffer srcHost) Copies memory from Host to Array.static intcuMemcpyHtoA(long dstArray, long dstOffset, DoubleBuffer srcHost) Copies memory from Host to Array.static intcuMemcpyHtoA(long dstArray, long dstOffset, FloatBuffer srcHost) Copies memory from Host to Array.static intcuMemcpyHtoA(long dstArray, long dstOffset, IntBuffer srcHost) Copies memory from Host to Array.static intcuMemcpyHtoA(long dstArray, long dstOffset, LongBuffer srcHost) Copies memory from Host to Array.static intcuMemcpyHtoA(long dstArray, long dstOffset, ShortBuffer srcHost) Copies memory from Host to Array.static intcuMemcpyHtoA(long dstArray, long dstOffset, PointerBuffer srcHost) Copies memory from Host to Array.static intcuMemcpyHtoAAsync(long dstArray, long dstOffset, ByteBuffer srcHost, long hStream) Copies memory from Host to Array.static intcuMemcpyHtoAAsync(long dstArray, long dstOffset, DoubleBuffer srcHost, long hStream) Copies memory from Host to Array.static intcuMemcpyHtoAAsync(long dstArray, long dstOffset, FloatBuffer srcHost, long hStream) Copies memory from Host to Array.static intcuMemcpyHtoAAsync(long dstArray, long dstOffset, IntBuffer srcHost, long hStream) Copies memory from Host to Array.static intcuMemcpyHtoAAsync(long dstArray, long dstOffset, LongBuffer srcHost, long hStream) Copies memory from Host to Array.static intcuMemcpyHtoAAsync(long dstArray, long dstOffset, ShortBuffer srcHost, long hStream) Copies memory from Host to Array.static intcuMemcpyHtoAAsync(long dstArray, long dstOffset, PointerBuffer srcHost, long hStream) Copies memory from Host to Array.static intcuMemcpyHtoD(long dstDevice, ByteBuffer srcHost) Copies memory from Host to Device.static intcuMemcpyHtoD(long dstDevice, DoubleBuffer srcHost) Copies memory from Host to Device.static intcuMemcpyHtoD(long dstDevice, FloatBuffer srcHost) Copies memory from Host to Device.static intcuMemcpyHtoD(long dstDevice, IntBuffer srcHost) Copies memory from Host to Device.static intcuMemcpyHtoD(long dstDevice, LongBuffer srcHost) Copies memory from Host to Device.static intcuMemcpyHtoD(long dstDevice, ShortBuffer srcHost) Copies memory from Host to Device.static intcuMemcpyHtoD(long dstDevice, PointerBuffer srcHost) Copies memory from Host to Device.static intcuMemcpyHtoDAsync(long dstDevice, ByteBuffer srcHost, long hStream) Copies memory from Host to Device.static intcuMemcpyHtoDAsync(long dstDevice, DoubleBuffer srcHost, long hStream) Copies memory from Host to Device.static intcuMemcpyHtoDAsync(long dstDevice, FloatBuffer srcHost, long hStream) Copies memory from Host to Device.static intcuMemcpyHtoDAsync(long dstDevice, IntBuffer srcHost, long hStream) Copies memory from Host to Device.static intcuMemcpyHtoDAsync(long dstDevice, LongBuffer srcHost, long hStream) Copies memory from Host to Device.static intcuMemcpyHtoDAsync(long dstDevice, ShortBuffer srcHost, long hStream) Copies memory from Host to Device.static intcuMemcpyHtoDAsync(long dstDevice, PointerBuffer srcHost, long hStream) Copies memory from Host to Device.static intcuMemcpyPeer(long dstDevice, long dstContext, long srcDevice, long srcContext, long ByteCount) Copies device memory between two contexts.static intcuMemcpyPeerAsync(long dstDevice, long dstContext, long srcDevice, long srcContext, long ByteCount, long hStream) Copies device memory between two contexts asynchronously.static intcuMemCreate(LongBuffer handle, long size, CUmemAllocationProp prop, long flags) Create a CUDA memory handle representing a memory allocation of a given size described by the given properties.static intcuMemExportToShareableHandle(ByteBuffer shareableHandle, long handle, int handleType, long flags) Exports an allocation to a requested shareable handle type.static intcuMemExportToShareableHandle(PointerBuffer shareableHandle, long handle, int handleType, long flags) Exports an allocation to a requested shareable handle type.static intcuMemFree(long dptr) Frees device memory.static intcuMemFreeAsync(long dptr, long hStream) Frees memory with stream ordered semantics.static intFrees page-locked host memory.static intcuMemGetAccess(LongBuffer flags, CUmemLocation location, long ptr) Get the accessflagsset for the givenlocationandptr.static intcuMemGetAddressRange(PointerBuffer pbase, PointerBuffer psize, long dptr) Get information on memory allocations.static intcuMemGetAllocationGranularity(PointerBuffer granularity, CUmemAllocationProp prop, int option) Calculates either the minimal or recommended granularity.static intcuMemGetAllocationPropertiesFromHandle(CUmemAllocationProp prop, long handle) Retrieve the contents of the property structure defining properties for this handle.static intcuMemGetInfo(PointerBuffer free, PointerBuffer total) Gets free and total memory.static intcuMemHostAlloc(PointerBuffer pp, long bytesize, int Flags) Allocates page-locked host memory.static intcuMemHostGetDevicePointer(PointerBuffer pdptr, ByteBuffer p, int Flags) Passes back device pointer of mapped pinned memory.static intcuMemHostGetFlags(IntBuffer pFlags, ByteBuffer p) Passes back flags that were used for a pinned allocationstatic intcuMemHostRegister(ByteBuffer p, int Flags) Registers an existing host memory range for use by CUDA.static intUnregisters a memory range that was registered withMemHostRegister.static intcuMemImportFromShareableHandle(LongBuffer handle, long osHandle, int shHandleType) Imports an allocation from a requested shareable handle type.static intcuMemMap(long ptr, long size, long offset, long handle, long flags) Maps an allocation handle to a reserved virtual address range.static intcuMemMapArrayAsync(CUarrayMapInfo.Buffer mapInfoList, long hStream) Maps or unmaps subregions of sparse CUDA arrays and sparse CUDA mipmapped arrays.static intcuMemPoolCreate(PointerBuffer pool, CUmemPoolProps poolProps) Creates a memory pool.static intcuMemPoolDestroy(long pool) Destroys the specified memory pool.static intcuMemPoolExportPointer(CUmemPoolPtrExportData shareData_out, long ptr) Export data to share a memory pool allocation between processes.static intcuMemPoolExportToShareableHandle(ByteBuffer handle_out, long pool, int handleType, long flags) Exports a memory pool to the requested handle type.static intcuMemPoolExportToShareableHandle(PointerBuffer handle_out, long pool, int handleType, long flags) Exports a memory pool to the requested handle type.static intcuMemPoolGetAccess(IntBuffer flags, long memPool, CUmemLocation location) Returns the accessibility of a pool from a device.static intcuMemPoolGetAttribute(long pool, int attr, ByteBuffer value) Gets attributes of a memory pool.static intcuMemPoolGetAttribute(long pool, int attr, IntBuffer value) Gets attributes of a memory pool.static intcuMemPoolGetAttribute(long pool, int attr, LongBuffer value) Gets attributes of a memory pool.static intcuMemPoolImportFromShareableHandle(PointerBuffer pool_out, ByteBuffer handle, int handleType, long flags) Imports a memory pool from a shared handle.static intcuMemPoolImportFromShareableHandle(PointerBuffer pool_out, PointerBuffer handle, int handleType, long flags) Imports a memory pool from a shared handle.static intcuMemPoolImportPointer(PointerBuffer ptr_out, long pool, CUmemPoolPtrExportData shareData) Import a memory pool allocation from another process.static intcuMemPoolSetAccess(long pool, CUmemAccessDesc.Buffer map) Controls visibility of pools between devices.static intcuMemPoolSetAttribute(long pool, int attr, ByteBuffer value) Sets attributes of a memory pool.static intcuMemPoolSetAttribute(long pool, int attr, IntBuffer value) Sets attributes of a memory pool.static intcuMemPoolSetAttribute(long pool, int attr, LongBuffer value) Sets attributes of a memory pool.static intcuMemPoolTrimTo(long pool, long minBytesToKeep) Tries to release memory back to the OS.static intcuMemPrefetchAsync(long devPtr, long count, int dstDevice, long hStream) Prefetches memory to the specified destination device,static intcuMemRangeGetAttribute(ByteBuffer data, int attribute, long devPtr, long count) Query an attribute of a given memory range.static intcuMemRangeGetAttributes(PointerBuffer data, PointerBuffer dataSizes, IntBuffer attributes, long devPtr, long count) Query attributes of a given memory range.static intcuMemRelease(long handle) Release a memory handle representing a memory allocation which was previously allocated throughMemCreate.static intcuMemRetainAllocationHandle(LongBuffer handle, ByteBuffer addr) Given an addressaddr, returns the allocation handle of the backing memory allocation.static intcuMemSetAccess(long ptr, long size, CUmemAccessDesc.Buffer desc) Set the access flags for each location specified indescfor the given virtual address range.static intcuMemsetD16(long dstDevice, short us, long N) Initializes device memory.static intcuMemsetD16Async(long dstDevice, short us, long N, long hStream) Sets device memorystatic intcuMemsetD2D16(long dstDevice, long dstPitch, short us, long Width, long Height) Initializes device memory.static intcuMemsetD2D16Async(long dstDevice, long dstPitch, short us, long Width, long Height, long hStream) Sets device memory.static intcuMemsetD2D32(long dstDevice, long dstPitch, int ui, long Width, long Height) Initializes device memory.static intcuMemsetD2D32Async(long dstDevice, long dstPitch, int ui, long Width, long Height, long hStream) Sets device memory.static intcuMemsetD2D8(long dstDevice, long dstPitch, byte uc, long Width, long Height) Initializes device memory.static intcuMemsetD2D8Async(long dstDevice, long dstPitch, byte uc, long Width, long Height, long hStream) Sets device memory.static intcuMemsetD32(long dstDevice, int ui, long N) Initializes device memorystatic intcuMemsetD32Async(long dstDevice, int ui, long N, long hStream) Sets device memory.static intcuMemsetD8(long dstDevice, byte uc, long N) Initializes device memory.static intcuMemsetD8Async(long dstDevice, byte uc, long N, long hStream) Sets device memorystatic intcuMemUnmap(long ptr, long size) Unmap the backing memory of a given address range.static intcuMipmappedArrayCreate(PointerBuffer pHandle, CUDA_ARRAY3D_DESCRIPTOR pMipmappedArrayDesc, int numMipmapLevels) Creates a CUDA mipmapped array.static intcuMipmappedArrayDestroy(long hMipmappedArray) Destroys a CUDA mipmapped array.static intcuMipmappedArrayGetLevel(PointerBuffer pLevelArray, long hMipmappedArray, int level) Gets a mipmap level of a CUDA mipmapped array.static intcuMipmappedArrayGetSparseProperties(CUDA_ARRAY_SPARSE_PROPERTIES sparseProperties, long mipmap) Returns the layout properties of a sparse CUDA mipmapped array.static intcuModuleGetFunction(PointerBuffer hfunc, long hmod, CharSequence name) Returns a function handle.static intcuModuleGetFunction(PointerBuffer hfunc, long hmod, ByteBuffer name) Returns a function handle.static intcuModuleGetGlobal(PointerBuffer dptr, PointerBuffer bytes, long hmod, CharSequence name) Returns a global pointer from a module.static intcuModuleGetGlobal(PointerBuffer dptr, PointerBuffer bytes, long hmod, ByteBuffer name) Returns a global pointer from a module.static intcuModuleGetSurfRef(PointerBuffer pSurfRef, long hmod, CharSequence name) Returns a handle to a surface reference.static intcuModuleGetSurfRef(PointerBuffer pSurfRef, long hmod, ByteBuffer name) Returns a handle to a surface reference.static intcuModuleGetTexRef(PointerBuffer pTexRef, long hmod, CharSequence name) Returns a handle to a texture reference.static intcuModuleGetTexRef(PointerBuffer pTexRef, long hmod, ByteBuffer name) Returns a handle to a texture reference.static intcuModuleLoad(PointerBuffer module, CharSequence fname) Loads a compute module.static intcuModuleLoad(PointerBuffer module, ByteBuffer fname) Loads a compute module.static intcuModuleLoadData(PointerBuffer module, ByteBuffer image) Load a module's data.static intcuModuleLoadDataEx(PointerBuffer module, ByteBuffer image, IntBuffer options, PointerBuffer optionValues) Load a module's data with options.static intcuModuleLoadFatBinary(PointerBuffer module, ByteBuffer fatCubin) Load a module's data.static intcuModuleUnload(long hmod) Unloads a module.static intcuOccupancyAvailableDynamicSMemPerBlock(PointerBuffer dynamicSmemSize, long func, int numBlocks, int blockSize) Returns dynamic shared memory available per block when launchingnumBlocksblocks on SM.static intcuOccupancyMaxActiveBlocksPerMultiprocessor(IntBuffer numBlocks, long func, int blockSize, long dynamicSMemSize) Returns occupancy of a function.static intcuOccupancyMaxActiveBlocksPerMultiprocessorWithFlags(IntBuffer numBlocks, long func, int blockSize, long dynamicSMemSize, int flags) Returns occupancy of a function.static intcuOccupancyMaxPotentialBlockSize(IntBuffer minGridSize, IntBuffer blockSize, long func, CUoccupancyB2DSizeI blockSizeToDynamicSMemSize, long dynamicSMemSize, int blockSizeLimit) Suggest a launch configuration with reasonable occupancy.static intcuOccupancyMaxPotentialBlockSizeWithFlags(IntBuffer minGridSize, IntBuffer blockSize, long func, CUoccupancyB2DSizeI blockSizeToDynamicSMemSize, long dynamicSMemSize, int blockSizeLimit, int flags) Suggest a launch configuration with reasonable occupancy.static intcuParamSetf(long hfunc, int offset, float value) Adds a floating-point parameter to the function's argument list.static intcuParamSeti(long hfunc, int offset, int value) Adds an integer parameter to the function's argument listDeprecated:static intcuParamSetSize(long hfunc, int numbytes) Sets the parameter size for the function.static intcuParamSetTexRef(long hfunc, int texunit, long hTexRef) Adds a texture-reference to the function's argument list.static intcuParamSetv(long hfunc, int offset, ByteBuffer ptr) Adds arbitrary data to the function's argument list.static intcuPointerGetAttribute(ByteBuffer data, int attribute, long ptr) Returns information about a pointer.static intcuPointerGetAttribute(IntBuffer data, int attribute, long ptr) Returns information about a pointer.static intcuPointerGetAttribute(LongBuffer data, int attribute, long ptr) Returns information about a pointer.static intcuPointerGetAttribute(PointerBuffer data, int attribute, long ptr) Returns information about a pointer.static intcuPointerGetAttributes(IntBuffer attributes, PointerBuffer data, long ptr) Returns information about a pointer.static intcuPointerSetAttribute(ByteBuffer value, int attribute, long ptr) Set attributes on a previously allocated memory region.static intcuSignalExternalSemaphoresAsync(PointerBuffer extSemArray, CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS.Buffer paramsArray, long stream) Signals a set of external semaphore objects,static intcuStreamAddCallback(long hStream, CUstreamCallbackI callback, long userData, int flags) Add a callback to a compute stream.static intcuStreamAttachMemAsync(long hStream, long dptr, long length, int flags) Attach memory to a stream asynchronously.static intcuStreamBatchMemOp(long stream, CUstreamBatchMemOpParams.Buffer paramArray, int flags) Batch operations to synchronize the stream via memory operations.static intcuStreamBeginCapture(long hStream) Begins graph capture on a stream.static intcuStreamBeginCapture_v2(long hStream, int mode) Begins graph capture on a stream.static intcuStreamCopyAttributes(long dst, long src) Copies attributes from source stream to destination stream.static intcuStreamCreate(PointerBuffer phStream, int Flags) Create a stream.static intcuStreamCreateWithPriority(PointerBuffer phStream, int flags, int priority) Create a stream with the given priority.static intcuStreamDestroy(long hStream) Destroys a stream.static intcuStreamEndCapture(long hStream, PointerBuffer phGraph) Ends capture on a stream, returning the captured graph.static intcuStreamGetAttribute(long hStream, int attr, CUstreamAttrValue value_out) Queries stream attribute.static intcuStreamGetCaptureInfo(long hStream, IntBuffer captureStatus, LongBuffer id) Query capture status of a stream.static intcuStreamGetCaptureInfo_v2(long hStream, IntBuffer captureStatus_out, LongBuffer id_out, PointerBuffer graph_out, PointerBuffer dependencies_out, PointerBuffer numDependencies_out) Query a stream's capture state (11.3+).static intcuStreamGetCtx(long hStream, PointerBuffer pctx) Query the context associated with a stream.static intcuStreamGetFlags(long hStream, IntBuffer flags) Query the flags of a given stream.static intcuStreamGetPriority(long hStream, IntBuffer priority) Query the priority of a given stream.static intcuStreamIsCapturing(long hStream, IntBuffer captureStatus) Returns a stream's capture status.static intcuStreamQuery(long hStream) Determine status of a compute stream.static intcuStreamSetAttribute(long hStream, int attr, CUstreamAttrValue value) Sets stream attribute.static intcuStreamSynchronize(long hStream) Wait until a stream's tasks are completed.static intcuStreamUpdateCaptureDependencies(long hStream, PointerBuffer dependencies, int flags) Update the set of dependencies in a capturing stream (11.3+).static intcuStreamWaitEvent(long hStream, long hEvent, int Flags) Make a compute stream wait on an event.static intcuStreamWaitValue32(long stream, long addr, int value, int flags) Wait on a memory location.static intcuStreamWaitValue64(long stream, long addr, long value, int flags) Wait on a memory location.static intcuStreamWriteValue32(long stream, long addr, int value, int flags) Write a value to memory.static intcuStreamWriteValue64(long stream, long addr, long value, int flags) Write a value to memory.static intcuSurfObjectCreate(LongBuffer pSurfObject, CUDA_RESOURCE_DESC pResDesc) Creates a surface object.static intcuSurfObjectDestroy(long surfObject) Destroys a surface object.static intcuSurfObjectGetResourceDesc(CUDA_RESOURCE_DESC pResDesc, long surfObject) Returns a surface object's resource descriptor.static intcuSurfRefGetArray(PointerBuffer phArray, long hSurfRef) Passes back the CUDA array bound to a surface reference.static intcuSurfRefSetArray(long hSurfRef, long hArray, int Flags) Sets the CUDA array for a surface reference.Deprecated:static intcuTexObjectCreate(LongBuffer pTexObject, CUDA_RESOURCE_DESC pResDesc, CUDA_TEXTURE_DESC pTexDesc, CUDA_RESOURCE_VIEW_DESC pResViewDesc) Creates a texture object.static intcuTexObjectDestroy(long texObject) Destroys a texture object.static intcuTexObjectGetResourceDesc(CUDA_RESOURCE_DESC pResDesc, long texObject) Returns a texture object's resource descriptor.static intcuTexObjectGetResourceViewDesc(CUDA_RESOURCE_VIEW_DESC pResViewDesc, long texObject) Returns a texture object's resource view descriptor.static intcuTexObjectGetTextureDesc(CUDA_TEXTURE_DESC pTexDesc, long texObject) Returns a texture object's texture descriptor.static intcuTexRefCreate(PointerBuffer pTexRef) Creates a texture reference.static intcuTexRefDestroy(long hTexRef) Destroys a texture reference.static intcuTexRefGetAddress(PointerBuffer pdptr, long hTexRef) Gets the address associated with a texture reference.static intcuTexRefGetAddressMode(IntBuffer pam, long hTexRef, int dim) Gets the addressing mode used by a texture reference.static intcuTexRefGetArray(PointerBuffer phArray, long hTexRef) Gets the array bound to a texture reference.static intcuTexRefGetBorderColor(FloatBuffer pBorderColor, long hTexRef) Gets the border color used by a texture reference.static intcuTexRefGetFilterMode(IntBuffer pfm, long hTexRef) Gets the filter-mode used by a texture reference.static intcuTexRefGetFlags(IntBuffer pFlags, long hTexRef) Gets the flags used by a texture reference.static intcuTexRefGetFormat(IntBuffer pFormat, IntBuffer pNumChannels, long hTexRef) Gets the format used by a texture reference.static intcuTexRefGetMaxAnisotropy(IntBuffer pmaxAniso, long hTexRef) Gets the maximum anisotropy for a texture reference.static intcuTexRefGetMipmapFilterMode(IntBuffer pfm, long hTexRef) Gets the mipmap filtering mode for a texture reference.static intcuTexRefGetMipmapLevelBias(FloatBuffer pbias, long hTexRef) Gets the mipmap level bias for a texture reference.static intcuTexRefGetMipmapLevelClamp(FloatBuffer pminMipmapLevelClamp, FloatBuffer pmaxMipmapLevelClamp, long hTexRef) Gets the min/max mipmap level clamps for a texture reference.static intcuTexRefGetMipmappedArray(PointerBuffer phMipmappedArray, long hTexRef) Gets the mipmapped array bound to a texture reference.static intcuTexRefSetAddress(PointerBuffer ByteOffset, long hTexRef, long dptr, long bytes) Binds an address as a texture reference.static intcuTexRefSetAddress2D(long hTexRef, CUDA_ARRAY_DESCRIPTOR desc, long dptr, long Pitch) Binds an address as a 2D texture reference.static intcuTexRefSetAddressMode(long hTexRef, int dim, int am) Sets the addressing mode for a texture reference.static intcuTexRefSetArray(long hTexRef, long hArray, int Flags) Binds an array as a texture reference.static intcuTexRefSetBorderColor(long hTexRef, FloatBuffer pBorderColor) Sets the border color for a texture reference.static intcuTexRefSetFilterMode(long hTexRef, int fm) Sets the filtering mode for a texture reference.static intcuTexRefSetFlags(long hTexRef, int Flags) Sets the flags for a texture reference.static intcuTexRefSetFormat(long hTexRef, int fmt, int NumPackedComponents) Sets the format for a texture reference.static intcuTexRefSetMaxAnisotropy(long hTexRef, int maxAniso) Sets the maximum anisotropy for a texture reference.static intcuTexRefSetMipmapFilterMode(long hTexRef, int fm) Sets the mipmap filtering mode for a texture reference (Deprecated)static intcuTexRefSetMipmapLevelBias(long hTexRef, float bias) Sets the mipmap level bias for a texture reference.static intcuTexRefSetMipmapLevelClamp(long hTexRef, float minMipmapLevelClamp, float maxMipmapLevelClamp) Sets the mipmap min/max mipmap level clamps for a texture reference.static intcuTexRefSetMipmappedArray(long hTexRef, long hMipmappedArray, int Flags) Binds a mipmapped array to a texture reference.static intSwaps the stream capture interaction mode for a thread.static intcuUserObjectCreate(PointerBuffer object_out, long ptr, CUhostFnI destroy, int initialRefcount, int flags) Create a user object.static intcuUserObjectRelease(long object, int count) Release a reference to a user object.static intcuUserObjectRetain(long object, int count) Retain a reference to a user object.static intcuWaitExternalSemaphoresAsync(PointerBuffer extSemArray, CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS.Buffer paramsArray, long stream) Waits on a set of external semaphore objects.static SharedLibraryReturns the NVCUDASharedLibrary.static intncuArray3DCreate(long pHandle, long pAllocateArray) Unsafe version of:Array3DCreatestatic intncuArray3DGetDescriptor(long pArrayDescriptor, long hArray) Unsafe version of:Array3DGetDescriptorstatic intncuArrayCreate(long pHandle, long pAllocateArray) Unsafe version of:ArrayCreatestatic intncuArrayGetDescriptor(long pArrayDescriptor, long hArray) Unsafe version of:ArrayGetDescriptorstatic intncuArrayGetPlane(long pPlaneArray, long hArray, int planeIdx) Unsafe version of:ArrayGetPlanestatic intncuArrayGetSparseProperties(long sparseProperties, long array) Unsafe version of:ArrayGetSparsePropertiesstatic intncuCtxAttach(long pctx, int flags) Unsafe version of:CtxAttachstatic intncuCtxCreate(long pctx, int flags, int dev) Unsafe version of:CtxCreatestatic intncuCtxCreate_v3(long pctx, long paramsArray, int numParams, int flags, int dev) Unsafe version of:CtxCreate_v3static intncuCtxGetApiVersion(long ctx, long version) Unsafe version of:CtxGetApiVersionstatic intncuCtxGetCacheConfig(long pconfig) Unsafe version of:CtxGetCacheConfigstatic intncuCtxGetCurrent(long pctx) Unsafe version of:CtxGetCurrentstatic intncuCtxGetDevice(long device) Unsafe version of:CtxGetDevicestatic intncuCtxGetExecAffinity(long pExecAffinity, int type) Unsafe version of:CtxGetExecAffinitystatic intncuCtxGetFlags(long flags) Unsafe version of:CtxGetFlagsstatic intncuCtxGetLimit(long pvalue, int limit) Unsafe version of:CtxGetLimitstatic intncuCtxGetSharedMemConfig(long pConfig) Unsafe version of:CtxGetSharedMemConfigstatic intncuCtxGetStreamPriorityRange(long leastPriority, long greatestPriority) Unsafe version of:CtxGetStreamPriorityRangestatic intncuCtxPopCurrent(long pctx) Unsafe version of:CtxPopCurrentstatic intncuDeviceCanAccessPeer(long canAccessPeer, int dev, int peerDev) Unsafe version of:DeviceCanAccessPeerstatic intncuDeviceComputeCapability(long major, long minor, int dev) Unsafe version of:DeviceComputeCapabilitystatic intncuDeviceGet(long device, int ordinal) Unsafe version of:DeviceGetstatic intncuDeviceGetAttribute(long pi, int attrib, int dev) Unsafe version of:DeviceGetAttributestatic intncuDeviceGetByPCIBusId(long dev, long pciBusId) Unsafe version of:DeviceGetByPCIBusIdstatic intncuDeviceGetCount(long count) Unsafe version of:DeviceGetCountstatic intncuDeviceGetDefaultMemPool(long pool_out, int dev) Unsafe version of:DeviceGetDefaultMemPoolstatic intncuDeviceGetExecAffinitySupport(long pi, int type, int dev) Unsafe version of:DeviceGetExecAffinitySupportstatic intncuDeviceGetGraphMemAttribute(int device, int attr, long value) Unsafe version of:DeviceGetGraphMemAttributestatic intncuDeviceGetLuid(long luid, long deviceNodeMask, int dev) Unsafe version of:DeviceGetLuidstatic intncuDeviceGetMemPool(long pool, int dev) Unsafe version of:DeviceGetMemPoolstatic intncuDeviceGetName(long name, int len, int dev) Unsafe version of:DeviceGetNamestatic intncuDeviceGetNvSciSyncAttributes(long nvSciSyncAttrList, int dev, int flags) Unsafe version of:DeviceGetNvSciSyncAttributesstatic intncuDeviceGetP2PAttribute(long value, int attrib, int srcDevice, int dstDevice) Unsafe version of:DeviceGetP2PAttributestatic intncuDeviceGetPCIBusId(long pciBusId, int len, int dev) Unsafe version of:DeviceGetPCIBusIdstatic intncuDeviceGetProperties(long prop, int dev) Unsafe version of:DeviceGetPropertiesstatic intncuDeviceGetTexture1DLinearMaxWidth(long maxWidthInElements, int format, int numChannels, int dev) Unsafe version of:DeviceGetTexture1DLinearMaxWidthstatic intncuDeviceGetUuid(long uuid, int dev) Unsafe version of:DeviceGetUuidstatic intncuDeviceGetUuid_v2(long uuid, int dev) Unsafe version of:DeviceGetUuid_v2static intncuDevicePrimaryCtxGetState(int dev, long flags, long active) Unsafe version of:DevicePrimaryCtxGetStatestatic intncuDevicePrimaryCtxRetain(long pctx, int dev) Unsafe version of:DevicePrimaryCtxRetainstatic intncuDeviceSetGraphMemAttribute(int device, int attr, long value) Unsafe version of:DeviceSetGraphMemAttributestatic intncuDeviceTotalMem(long bytes, int dev) Unsafe version of:DeviceTotalMemstatic intncuDriverGetVersion(long driverVersion) Unsafe version of:DriverGetVersionstatic intncuEventCreate(long phEvent, int Flags) Unsafe version of:EventCreatestatic intncuEventElapsedTime(long pMilliseconds, long hStart, long hEnd) Unsafe version of:EventElapsedTimestatic intncuExternalMemoryGetMappedBuffer(long devPtr, long extMem, long bufferDesc) Unsafe version of:ExternalMemoryGetMappedBufferstatic intncuExternalMemoryGetMappedMipmappedArray(long mipmap, long extMem, long mipmapDesc) Unsafe version of:ExternalMemoryGetMappedMipmappedArraystatic intncuFuncGetAttribute(long pi, int attrib, long hfunc) Unsafe version of:FuncGetAttributestatic intncuFuncGetModule(long hmod, long hfunc) Unsafe version of:FuncGetModulestatic intncuGetErrorName(int error, long pStr) Unsafe version of:GetErrorNamestatic intncuGetErrorString(int error, long pStr) Unsafe version of:GetErrorStringstatic intncuGetExportTable(long ppExportTable, long pExportTableId) static intncuGetProcAddress(long symbol, long pfn, int cudaVersion, long flags) Unsafe version of:GetProcAddressstatic intncuGraphAddChildGraphNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long childGraph) Unsafe version of:GraphAddChildGraphNodestatic intncuGraphAddDependencies(long hGraph, long from, long to, long numDependencies) Unsafe version of:GraphAddDependenciesstatic intncuGraphAddEmptyNode(long phGraphNode, long hGraph, long dependencies, long numDependencies) Unsafe version of:GraphAddEmptyNodestatic intncuGraphAddEventRecordNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long event) Unsafe version of:GraphAddEventRecordNodestatic intncuGraphAddEventWaitNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long event) Unsafe version of:GraphAddEventWaitNodestatic intncuGraphAddExternalSemaphoresSignalNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long nodeParams) Unsafe version of:GraphAddExternalSemaphoresSignalNodestatic intncuGraphAddExternalSemaphoresWaitNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long nodeParams) Unsafe version of:GraphAddExternalSemaphoresWaitNodestatic intncuGraphAddHostNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long nodeParams) Unsafe version of:GraphAddHostNodestatic intncuGraphAddKernelNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long nodeParams) Unsafe version of:GraphAddKernelNodestatic intncuGraphAddMemAllocNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long nodeParams) Unsafe version of:GraphAddMemAllocNodestatic intncuGraphAddMemcpyNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long copyParams, long ctx) Unsafe version of:GraphAddMemcpyNodestatic intncuGraphAddMemFreeNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long dptr) Unsafe version of:GraphAddMemFreeNodestatic intncuGraphAddMemsetNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long memsetParams, long ctx) Unsafe version of:GraphAddMemsetNodestatic intncuGraphChildGraphNodeGetGraph(long hNode, long phGraph) Unsafe version of:GraphChildGraphNodeGetGraphstatic intncuGraphClone(long phGraphClone, long originalGraph) Unsafe version of:GraphClonestatic intncuGraphCreate(long phGraph, int flags) Unsafe version of:GraphCreatestatic intncuGraphDebugDotPrint(long hGraph, long path, int flags) Unsafe version of:GraphDebugDotPrintstatic intncuGraphEventRecordNodeGetEvent(long hNode, long event_out) Unsafe version of:GraphEventRecordNodeGetEventstatic intncuGraphEventWaitNodeGetEvent(long hNode, long event_out) Unsafe version of:GraphEventWaitNodeGetEventstatic intncuGraphExecExternalSemaphoresSignalNodeSetParams(long hGraphExec, long hNode, long nodeParams) Unsafe version of:GraphExecExternalSemaphoresSignalNodeSetParamsstatic intncuGraphExecExternalSemaphoresWaitNodeSetParams(long hGraphExec, long hNode, long nodeParams) Unsafe version of:GraphExecExternalSemaphoresWaitNodeSetParamsstatic intncuGraphExecHostNodeSetParams(long hGraphExec, long hNode, long nodeParams) Unsafe version of:GraphExecHostNodeSetParamsstatic intncuGraphExecKernelNodeSetParams(long hGraphExec, long hNode, long nodeParams) Unsafe version of:GraphExecKernelNodeSetParamsstatic intncuGraphExecMemcpyNodeSetParams(long hGraphExec, long hNode, long copyParams, long ctx) Unsafe version of:GraphExecMemcpyNodeSetParamsstatic intncuGraphExecMemsetNodeSetParams(long hGraphExec, long hNode, long memsetParams, long ctx) Unsafe version of:GraphExecMemsetNodeSetParamsstatic intncuGraphExecUpdate(long hGraphExec, long hGraph, long hErrorNode_out, long updateResult_out) Unsafe version of:GraphExecUpdatestatic intncuGraphExternalSemaphoresSignalNodeGetParams(long hNode, long params_out) Unsafe version of:GraphExternalSemaphoresSignalNodeGetParamsstatic intncuGraphExternalSemaphoresSignalNodeSetParams(long hNode, long nodeParams) Unsafe version of:GraphExternalSemaphoresSignalNodeSetParamsstatic intncuGraphExternalSemaphoresWaitNodeGetParams(long hNode, long params_out) Unsafe version of:GraphExternalSemaphoresWaitNodeGetParamsstatic intncuGraphExternalSemaphoresWaitNodeSetParams(long hNode, long nodeParams) Unsafe version of:GraphExternalSemaphoresWaitNodeSetParamsstatic intncuGraphGetEdges(long hGraph, long from, long to, long numEdges) Unsafe version of:GraphGetEdgesstatic intncuGraphGetNodes(long hGraph, long nodes, long numNodes) Unsafe version of:GraphGetNodesstatic intncuGraphGetRootNodes(long hGraph, long rootNodes, long numRootNodes) Unsafe version of:GraphGetRootNodesstatic intncuGraphHostNodeGetParams(long hNode, long nodeParams) Unsafe version of:GraphHostNodeGetParamsstatic intncuGraphHostNodeSetParams(long hNode, long nodeParams) Unsafe version of:GraphHostNodeSetParamsstatic intncuGraphicsMapResources(int count, long resources, long hStream) Unsafe version of:GraphicsMapResourcesstatic intncuGraphicsResourceGetMappedMipmappedArray(long pMipmappedArray, long resource) Unsafe version of:GraphicsResourceGetMappedMipmappedArraystatic intncuGraphicsResourceGetMappedPointer(long pDevPtr, long pSize, long resource) Unsafe version of:GraphicsResourceGetMappedPointerstatic intncuGraphicsSubResourceGetMappedArray(long pArray, long resource, int arrayIndex, int mipLevel) Unsafe version of:GraphicsSubResourceGetMappedArraystatic intncuGraphicsUnmapResources(int count, long resources, long hStream) Unsafe version of:GraphicsUnmapResourcesstatic intncuGraphInstantiate(long phGraphExec, long hGraph, long phErrorNode, long logBuffer, long bufferSize) Unsafe version of:GraphInstantiatestatic intncuGraphInstantiateWithFlags(long phGraphExec, long hGraph, long flags) Unsafe version of:GraphInstantiateWithFlagsstatic intncuGraphKernelNodeGetAttribute(long hNode, int attr, long value_out) Unsafe version of:GraphKernelNodeGetAttributestatic intncuGraphKernelNodeGetParams(long hNode, long nodeParams) Unsafe version of:GraphKernelNodeGetParamsstatic intncuGraphKernelNodeSetAttribute(long hNode, int attr, long value) Unsafe version of:GraphKernelNodeSetAttributestatic intncuGraphKernelNodeSetParams(long hNode, long nodeParams) Unsafe version of:GraphKernelNodeSetParamsstatic intncuGraphMemAllocNodeGetParams(long hNode, long params_out) Unsafe version of:GraphMemAllocNodeGetParamsstatic intncuGraphMemcpyNodeGetParams(long hNode, long nodeParams) Unsafe version of:GraphMemcpyNodeGetParamsstatic intncuGraphMemcpyNodeSetParams(long hNode, long nodeParams) Unsafe version of:GraphMemcpyNodeSetParamsstatic intncuGraphMemFreeNodeGetParams(long hNode, long dptr_out) Unsafe version of:GraphMemFreeNodeGetParamsstatic intncuGraphMemsetNodeGetParams(long hNode, long nodeParams) Unsafe version of:GraphMemsetNodeGetParamsstatic intncuGraphMemsetNodeSetParams(long hNode, long nodeParams) Unsafe version of:GraphMemsetNodeSetParamsstatic intncuGraphNodeFindInClone(long phNode, long hOriginalNode, long hClonedGraph) Unsafe version of:GraphNodeFindInClonestatic intncuGraphNodeGetDependencies(long hNode, long dependencies, long numDependencies) Unsafe version of:GraphNodeGetDependenciesstatic intncuGraphNodeGetDependentNodes(long hNode, long dependentNodes, long numDependentNodes) Unsafe version of:GraphNodeGetDependentNodesstatic intncuGraphNodeGetType(long hNode, long type) Unsafe version of:GraphNodeGetTypestatic intncuGraphRemoveDependencies(long hGraph, long from, long to, long numDependencies) Unsafe version of:GraphRemoveDependenciesstatic intncuImportExternalMemory(long extMem_out, long memHandleDesc) Unsafe version of:ImportExternalMemorystatic intncuImportExternalSemaphore(long extSem_out, long semHandleDesc) Unsafe version of:ImportExternalSemaphorestatic intncuIpcGetEventHandle(long pHandle, long event) Unsafe version of:IpcGetEventHandlestatic intncuIpcGetMemHandle(long pHandle, long dptr) Unsafe version of:IpcGetMemHandlestatic intncuIpcOpenEventHandle(long phEvent, long handle) Unsafe version of:IpcOpenEventHandlestatic intncuIpcOpenMemHandle(long pdptr, long handle, int Flags) Unsafe version of:IpcOpenMemHandlestatic intncuLaunchCooperativeKernel(long f, int gridDimX, int gridDimY, int gridDimZ, int blockDimX, int blockDimY, int blockDimZ, int sharedMemBytes, long hStream, long kernelParams) Unsafe version of:LaunchCooperativeKernelstatic intncuLaunchCooperativeKernelMultiDevice(long launchParamsList, int numDevices, int flags) Unsafe version of:LaunchCooperativeKernelMultiDevicestatic intncuLaunchHostFunc(long hStream, long fn, long userData) Unsafe version of:LaunchHostFuncstatic intncuLaunchKernel(long f, int gridDimX, int gridDimY, int gridDimZ, int blockDimX, int blockDimY, int blockDimZ, int sharedMemBytes, long hStream, long kernelParams, long extra) Unsafe version of:LaunchKernelstatic intncuLinkAddData(long state, int type, long data, long size, long name, int numOptions, long options, long optionValues) Unsafe version of:LinkAddDatastatic intncuLinkAddFile(long state, int type, long path, int numOptions, long options, long optionValues) Unsafe version of:LinkAddFilestatic intncuLinkComplete(long state, long cubinOut, long sizeOut) Unsafe version of:LinkCompletestatic intncuLinkCreate(int numOptions, long options, long optionValues, long stateOut) Unsafe version of:LinkCreatestatic intncuMemAddressReserve(long ptr, long size, long alignment, long addr, long flags) Unsafe version of:MemAddressReservestatic intncuMemAlloc(long dptr, long bytesize) Unsafe version of:MemAllocstatic intncuMemAllocAsync(long dptr, long bytesize, long hStream) Unsafe version of:MemAllocAsyncstatic intncuMemAllocFromPoolAsync(long dptr, long bytesize, long pool, long hStream) Unsafe version of:MemAllocFromPoolAsyncstatic intncuMemAllocHost(long pp, long bytesize) Unsafe version of:MemAllocHoststatic intncuMemAllocManaged(long dptr, long bytesize, int flags) Unsafe version of:MemAllocManagedstatic intncuMemAllocPitch(long dptr, long pPitch, long WidthInBytes, long Height, int ElementSizeBytes) Unsafe version of:MemAllocPitchstatic intncuMemcpy2D(long pCopy) Unsafe version of:Memcpy2Dstatic intncuMemcpy2DAsync(long pCopy, long hStream) Unsafe version of:Memcpy2DAsyncstatic intncuMemcpy2DUnaligned(long pCopy) Unsafe version of:Memcpy2DUnalignedstatic intncuMemcpy3D(long pCopy) Unsafe version of:Memcpy3Dstatic intncuMemcpy3DAsync(long pCopy, long hStream) Unsafe version of:Memcpy3DAsyncstatic intncuMemcpy3DPeer(long pCopy) Unsafe version of:Memcpy3DPeerstatic intncuMemcpy3DPeerAsync(long pCopy, long hStream) Unsafe version of:Memcpy3DPeerAsyncstatic intncuMemcpyAtoH(long dstHost, long srcArray, long srcOffset, long ByteCount) Unsafe version of:MemcpyAtoHstatic intncuMemcpyAtoHAsync(long dstHost, long srcArray, long srcOffset, long ByteCount, long hStream) Unsafe version of:MemcpyAtoHAsyncstatic intncuMemcpyDtoH(long dstHost, long srcDevice, long ByteCount) Unsafe version of:MemcpyDtoHstatic intncuMemcpyDtoHAsync(long dstHost, long srcDevice, long ByteCount, long hStream) Unsafe version of:MemcpyDtoHAsyncstatic intncuMemcpyHtoA(long dstArray, long dstOffset, long srcHost, long ByteCount) Unsafe version of:MemcpyHtoAstatic intncuMemcpyHtoAAsync(long dstArray, long dstOffset, long srcHost, long ByteCount, long hStream) Unsafe version of:MemcpyHtoAAsyncstatic intncuMemcpyHtoD(long dstDevice, long srcHost, long ByteCount) Unsafe version of:MemcpyHtoDstatic intncuMemcpyHtoDAsync(long dstDevice, long srcHost, long ByteCount, long hStream) Unsafe version of:MemcpyHtoDAsyncstatic intncuMemCreate(long handle, long size, long prop, long flags) Unsafe version of:MemCreatestatic intncuMemExportToShareableHandle(long shareableHandle, long handle, int handleType, long flags) Unsafe version of:MemExportToShareableHandlestatic intncuMemFreeHost(long p) Unsafe version of:MemFreeHoststatic intncuMemGetAccess(long flags, long location, long ptr) Unsafe version of:MemGetAccessstatic intncuMemGetAddressRange(long pbase, long psize, long dptr) Unsafe version of:MemGetAddressRangestatic intncuMemGetAllocationGranularity(long granularity, long prop, int option) Unsafe version of:MemGetAllocationGranularitystatic intncuMemGetAllocationPropertiesFromHandle(long prop, long handle) Unsafe version of:MemGetAllocationPropertiesFromHandlestatic intncuMemGetInfo(long free, long total) Unsafe version of:MemGetInfostatic intncuMemHostAlloc(long pp, long bytesize, int Flags) Unsafe version of:MemHostAllocstatic intncuMemHostGetDevicePointer(long pdptr, long p, int Flags) Unsafe version of:MemHostGetDevicePointerstatic intncuMemHostGetFlags(long pFlags, long p) Unsafe version of:MemHostGetFlagsstatic intncuMemHostRegister(long p, long bytesize, int Flags) Unsafe version of:MemHostRegisterstatic intncuMemHostUnregister(long p) Unsafe version of:MemHostUnregisterstatic intncuMemImportFromShareableHandle(long handle, long osHandle, int shHandleType) Unsafe version of:MemImportFromShareableHandlestatic intncuMemMapArrayAsync(long mapInfoList, int count, long hStream) Unsafe version of:MemMapArrayAsyncstatic intncuMemPoolCreate(long pool, long poolProps) Unsafe version of:MemPoolCreatestatic intncuMemPoolExportPointer(long shareData_out, long ptr) Unsafe version of:MemPoolExportPointerstatic intncuMemPoolExportToShareableHandle(long handle_out, long pool, int handleType, long flags) Unsafe version of:MemPoolExportToShareableHandlestatic intncuMemPoolGetAccess(long flags, long memPool, long location) Unsafe version of:MemPoolGetAccessstatic intncuMemPoolGetAttribute(long pool, int attr, long value) Unsafe version of:MemPoolGetAttributestatic intncuMemPoolImportFromShareableHandle(long pool_out, long handle, int handleType, long flags) Unsafe version of:MemPoolImportFromShareableHandlestatic intncuMemPoolImportPointer(long ptr_out, long pool, long shareData) Unsafe version of:MemPoolImportPointerstatic intncuMemPoolSetAccess(long pool, long map, long count) Unsafe version of:MemPoolSetAccessstatic intncuMemPoolSetAttribute(long pool, int attr, long value) Unsafe version of:MemPoolSetAttributestatic intncuMemRangeGetAttribute(long data, long dataSize, int attribute, long devPtr, long count) Unsafe version of:MemRangeGetAttributestatic intncuMemRangeGetAttributes(long data, long dataSizes, long attributes, long numAttributes, long devPtr, long count) Unsafe version of:MemRangeGetAttributesstatic intncuMemRetainAllocationHandle(long handle, long addr) Unsafe version of:MemRetainAllocationHandlestatic intncuMemSetAccess(long ptr, long size, long desc, long count) Unsafe version of:MemSetAccessstatic intncuMipmappedArrayCreate(long pHandle, long pMipmappedArrayDesc, int numMipmapLevels) Unsafe version of:MipmappedArrayCreatestatic intncuMipmappedArrayGetLevel(long pLevelArray, long hMipmappedArray, int level) Unsafe version of:MipmappedArrayGetLevelstatic intncuMipmappedArrayGetSparseProperties(long sparseProperties, long mipmap) Unsafe version of:MipmappedArrayGetSparsePropertiesstatic intncuModuleGetFunction(long hfunc, long hmod, long name) Unsafe version of:ModuleGetFunctionstatic intncuModuleGetGlobal(long dptr, long bytes, long hmod, long name) Unsafe version of:ModuleGetGlobalstatic intncuModuleGetSurfRef(long pSurfRef, long hmod, long name) Unsafe version of:ModuleGetSurfRefstatic intncuModuleGetTexRef(long pTexRef, long hmod, long name) Unsafe version of:ModuleGetTexRefstatic intncuModuleLoad(long module, long fname) Unsafe version of:ModuleLoadstatic intncuModuleLoadData(long module, long image) Unsafe version of:ModuleLoadDatastatic intncuModuleLoadDataEx(long module, long image, int numOptions, long options, long optionValues) Unsafe version of:ModuleLoadDataExstatic intncuModuleLoadFatBinary(long module, long fatCubin) Unsafe version of:ModuleLoadFatBinarystatic intncuOccupancyAvailableDynamicSMemPerBlock(long dynamicSmemSize, long func, int numBlocks, int blockSize) Unsafe version of:OccupancyAvailableDynamicSMemPerBlockstatic intncuOccupancyMaxActiveBlocksPerMultiprocessor(long numBlocks, long func, int blockSize, long dynamicSMemSize) Unsafe version of:OccupancyMaxActiveBlocksPerMultiprocessorstatic intncuOccupancyMaxActiveBlocksPerMultiprocessorWithFlags(long numBlocks, long func, int blockSize, long dynamicSMemSize, int flags) Unsafe version of:OccupancyMaxActiveBlocksPerMultiprocessorWithFlagsstatic intncuOccupancyMaxPotentialBlockSize(long minGridSize, long blockSize, long func, long blockSizeToDynamicSMemSize, long dynamicSMemSize, int blockSizeLimit) Unsafe version of:OccupancyMaxPotentialBlockSizestatic intncuOccupancyMaxPotentialBlockSizeWithFlags(long minGridSize, long blockSize, long func, long blockSizeToDynamicSMemSize, long dynamicSMemSize, int blockSizeLimit, int flags) Unsafe version of:OccupancyMaxPotentialBlockSizeWithFlagsstatic intncuParamSetv(long hfunc, int offset, long ptr, int numbytes) Unsafe version of:ParamSetvstatic intncuPointerGetAttribute(long data, int attribute, long ptr) Unsafe version of:PointerGetAttributestatic intncuPointerGetAttributes(int numAttributes, long attributes, long data, long ptr) Unsafe version of:PointerGetAttributesstatic intncuPointerSetAttribute(long value, int attribute, long ptr) Unsafe version of:PointerSetAttributestatic intncuSignalExternalSemaphoresAsync(long extSemArray, long paramsArray, int numExtSems, long stream) Unsafe version of:SignalExternalSemaphoresAsyncstatic intncuStreamAddCallback(long hStream, long callback, long userData, int flags) Unsafe version of:StreamAddCallbackstatic intncuStreamBatchMemOp(long stream, int count, long paramArray, int flags) Unsafe version of:StreamBatchMemOpstatic intncuStreamCreate(long phStream, int Flags) Unsafe version of:StreamCreatestatic intncuStreamCreateWithPriority(long phStream, int flags, int priority) Unsafe version of:StreamCreateWithPrioritystatic intncuStreamEndCapture(long hStream, long phGraph) Unsafe version of:StreamEndCapturestatic intncuStreamGetAttribute(long hStream, int attr, long value_out) Unsafe version of:StreamGetAttributestatic intncuStreamGetCaptureInfo(long hStream, long captureStatus, long id) Unsafe version of:StreamGetCaptureInfostatic intncuStreamGetCaptureInfo_v2(long hStream, long captureStatus_out, long id_out, long graph_out, long dependencies_out, long numDependencies_out) Unsafe version of:StreamGetCaptureInfo_v2static intncuStreamGetCtx(long hStream, long pctx) Unsafe version of:StreamGetCtxstatic intncuStreamGetFlags(long hStream, long flags) Unsafe version of:StreamGetFlagsstatic intncuStreamGetPriority(long hStream, long priority) Unsafe version of:StreamGetPrioritystatic intncuStreamIsCapturing(long hStream, long captureStatus) Unsafe version of:StreamIsCapturingstatic intncuStreamSetAttribute(long hStream, int attr, long value) Unsafe version of:StreamSetAttributestatic intncuStreamUpdateCaptureDependencies(long hStream, long dependencies, long numDependencies, int flags) Unsafe version of:StreamUpdateCaptureDependenciesstatic intncuSurfObjectCreate(long pSurfObject, long pResDesc) Unsafe version of:SurfObjectCreatestatic intncuSurfObjectGetResourceDesc(long pResDesc, long surfObject) Unsafe version of:SurfObjectGetResourceDescstatic intncuSurfRefGetArray(long phArray, long hSurfRef) Unsafe version of:SurfRefGetArraystatic intncuTexObjectCreate(long pTexObject, long pResDesc, long pTexDesc, long pResViewDesc) Unsafe version of:TexObjectCreatestatic intncuTexObjectGetResourceDesc(long pResDesc, long texObject) Unsafe version of:TexObjectGetResourceDescstatic intncuTexObjectGetResourceViewDesc(long pResViewDesc, long texObject) Unsafe version of:TexObjectGetResourceViewDescstatic intncuTexObjectGetTextureDesc(long pTexDesc, long texObject) Unsafe version of:TexObjectGetTextureDescstatic intncuTexRefCreate(long pTexRef) Unsafe version of:TexRefCreatestatic intncuTexRefGetAddress(long pdptr, long hTexRef) Unsafe version of:TexRefGetAddressstatic intncuTexRefGetAddressMode(long pam, long hTexRef, int dim) Unsafe version of:TexRefGetAddressModestatic intncuTexRefGetArray(long phArray, long hTexRef) Unsafe version of:TexRefGetArraystatic intncuTexRefGetBorderColor(long pBorderColor, long hTexRef) Unsafe version of:TexRefGetBorderColorstatic intncuTexRefGetFilterMode(long pfm, long hTexRef) Unsafe version of:TexRefGetFilterModestatic intncuTexRefGetFlags(long pFlags, long hTexRef) Unsafe version of:TexRefGetFlagsstatic intncuTexRefGetFormat(long pFormat, long pNumChannels, long hTexRef) Unsafe version of:TexRefGetFormatstatic intncuTexRefGetMaxAnisotropy(long pmaxAniso, long hTexRef) Unsafe version of:TexRefGetMaxAnisotropystatic intncuTexRefGetMipmapFilterMode(long pfm, long hTexRef) Unsafe version of:TexRefGetMipmapFilterModestatic intncuTexRefGetMipmapLevelBias(long pbias, long hTexRef) Unsafe version of:TexRefGetMipmapLevelBiasstatic intncuTexRefGetMipmapLevelClamp(long pminMipmapLevelClamp, long pmaxMipmapLevelClamp, long hTexRef) Unsafe version of:TexRefGetMipmapLevelClampstatic intncuTexRefGetMipmappedArray(long phMipmappedArray, long hTexRef) Unsafe version of:TexRefGetMipmappedArraystatic intncuTexRefSetAddress(long ByteOffset, long hTexRef, long dptr, long bytes) Unsafe version of:TexRefSetAddressstatic intncuTexRefSetAddress2D(long hTexRef, long desc, long dptr, long Pitch) Unsafe version of:TexRefSetAddress2Dstatic intncuTexRefSetBorderColor(long hTexRef, long pBorderColor) Unsafe version of:TexRefSetBorderColorstatic intncuThreadExchangeStreamCaptureMode(long mode) Unsafe version of:ThreadExchangeStreamCaptureModestatic intncuUserObjectCreate(long object_out, long ptr, long destroy, int initialRefcount, int flags) Unsafe version of:UserObjectCreatestatic intncuWaitExternalSemaphoresAsync(long extSemArray, long paramsArray, int numExtSems, long stream) Unsafe version of:WaitExternalSemaphoresAsync
-
Field Details
-
CU_IPC_HANDLE_SIZE
public static final int CU_IPC_HANDLE_SIZE- See Also:
-
CU_IPC_MEM_LAZY_ENABLE_PEER_ACCESS
public static final int CU_IPC_MEM_LAZY_ENABLE_PEER_ACCESSCUDA Ipc Mem Flags. (CUipcMem_flags)Enum values:
IPC_MEM_LAZY_ENABLE_PEER_ACCESS- Automatically enable peer access between remote devices as needed
- See Also:
-
CU_MEM_ATTACH_GLOBAL
public static final int CU_MEM_ATTACH_GLOBALCUDA Mem Attach Flags. (CUmemAttach_flags)Enum values:
MEM_ATTACH_GLOBAL- Memory can be accessed by any stream on any deviceMEM_ATTACH_HOST- Memory cannot be accessed by any stream on any deviceMEM_ATTACH_SINGLE- Memory can only be accessed by a single stream on the associated device
- See Also:
-
CU_MEM_ATTACH_HOST
public static final int CU_MEM_ATTACH_HOSTCUDA Mem Attach Flags. (CUmemAttach_flags)Enum values:
MEM_ATTACH_GLOBAL- Memory can be accessed by any stream on any deviceMEM_ATTACH_HOST- Memory cannot be accessed by any stream on any deviceMEM_ATTACH_SINGLE- Memory can only be accessed by a single stream on the associated device
- See Also:
-
CU_MEM_ATTACH_SINGLE
public static final int CU_MEM_ATTACH_SINGLECUDA Mem Attach Flags. (CUmemAttach_flags)Enum values:
MEM_ATTACH_GLOBAL- Memory can be accessed by any stream on any deviceMEM_ATTACH_HOST- Memory cannot be accessed by any stream on any deviceMEM_ATTACH_SINGLE- Memory can only be accessed by a single stream on the associated device
- See Also:
-
CU_CTX_SCHED_AUTO
public static final int CU_CTX_SCHED_AUTOContext creation flags. (CUctx_flags)Enum values:
CTX_SCHED_AUTO- Automatic schedulingCTX_SCHED_SPIN- Set spin as default schedulingCTX_SCHED_YIELD- Set yield as default schedulingCTX_SCHED_BLOCKING_SYNC- Set blocking synchronization as default schedulingCTX_BLOCKING_SYNC- Set blocking synchronization as default scheduling. This flag was deprecated as of CUDA 4.0 and was replaced withCTX_SCHED_BLOCKING_SYNC.CTX_SCHED_MASKCTX_MAP_HOST- This flag was deprecated as of CUDA 11.0 and it no longer has any effect.All contexts as of CUDA 3.2 behave as though the flag is enabled.
CTX_LMEM_RESIZE_TO_MAX- Keep local memory allocation after launchCTX_FLAGS_MASK
- See Also:
-
CU_CTX_SCHED_SPIN
public static final int CU_CTX_SCHED_SPINContext creation flags. (CUctx_flags)Enum values:
CTX_SCHED_AUTO- Automatic schedulingCTX_SCHED_SPIN- Set spin as default schedulingCTX_SCHED_YIELD- Set yield as default schedulingCTX_SCHED_BLOCKING_SYNC- Set blocking synchronization as default schedulingCTX_BLOCKING_SYNC- Set blocking synchronization as default scheduling. This flag was deprecated as of CUDA 4.0 and was replaced withCTX_SCHED_BLOCKING_SYNC.CTX_SCHED_MASKCTX_MAP_HOST- This flag was deprecated as of CUDA 11.0 and it no longer has any effect.All contexts as of CUDA 3.2 behave as though the flag is enabled.
CTX_LMEM_RESIZE_TO_MAX- Keep local memory allocation after launchCTX_FLAGS_MASK
- See Also:
-
CU_CTX_SCHED_YIELD
public static final int CU_CTX_SCHED_YIELDContext creation flags. (CUctx_flags)Enum values:
CTX_SCHED_AUTO- Automatic schedulingCTX_SCHED_SPIN- Set spin as default schedulingCTX_SCHED_YIELD- Set yield as default schedulingCTX_SCHED_BLOCKING_SYNC- Set blocking synchronization as default schedulingCTX_BLOCKING_SYNC- Set blocking synchronization as default scheduling. This flag was deprecated as of CUDA 4.0 and was replaced withCTX_SCHED_BLOCKING_SYNC.CTX_SCHED_MASKCTX_MAP_HOST- This flag was deprecated as of CUDA 11.0 and it no longer has any effect.All contexts as of CUDA 3.2 behave as though the flag is enabled.
CTX_LMEM_RESIZE_TO_MAX- Keep local memory allocation after launchCTX_FLAGS_MASK
- See Also:
-
CU_CTX_SCHED_BLOCKING_SYNC
public static final int CU_CTX_SCHED_BLOCKING_SYNCContext creation flags. (CUctx_flags)Enum values:
CTX_SCHED_AUTO- Automatic schedulingCTX_SCHED_SPIN- Set spin as default schedulingCTX_SCHED_YIELD- Set yield as default schedulingCTX_SCHED_BLOCKING_SYNC- Set blocking synchronization as default schedulingCTX_BLOCKING_SYNC- Set blocking synchronization as default scheduling. This flag was deprecated as of CUDA 4.0 and was replaced withCTX_SCHED_BLOCKING_SYNC.CTX_SCHED_MASKCTX_MAP_HOST- This flag was deprecated as of CUDA 11.0 and it no longer has any effect.All contexts as of CUDA 3.2 behave as though the flag is enabled.
CTX_LMEM_RESIZE_TO_MAX- Keep local memory allocation after launchCTX_FLAGS_MASK
- See Also:
-
CU_CTX_BLOCKING_SYNC
public static final int CU_CTX_BLOCKING_SYNCContext creation flags. (CUctx_flags)Enum values:
CTX_SCHED_AUTO- Automatic schedulingCTX_SCHED_SPIN- Set spin as default schedulingCTX_SCHED_YIELD- Set yield as default schedulingCTX_SCHED_BLOCKING_SYNC- Set blocking synchronization as default schedulingCTX_BLOCKING_SYNC- Set blocking synchronization as default scheduling. This flag was deprecated as of CUDA 4.0 and was replaced withCTX_SCHED_BLOCKING_SYNC.CTX_SCHED_MASKCTX_MAP_HOST- This flag was deprecated as of CUDA 11.0 and it no longer has any effect.All contexts as of CUDA 3.2 behave as though the flag is enabled.
CTX_LMEM_RESIZE_TO_MAX- Keep local memory allocation after launchCTX_FLAGS_MASK
- See Also:
-
CU_CTX_SCHED_MASK
public static final int CU_CTX_SCHED_MASKContext creation flags. (CUctx_flags)Enum values:
CTX_SCHED_AUTO- Automatic schedulingCTX_SCHED_SPIN- Set spin as default schedulingCTX_SCHED_YIELD- Set yield as default schedulingCTX_SCHED_BLOCKING_SYNC- Set blocking synchronization as default schedulingCTX_BLOCKING_SYNC- Set blocking synchronization as default scheduling. This flag was deprecated as of CUDA 4.0 and was replaced withCTX_SCHED_BLOCKING_SYNC.CTX_SCHED_MASKCTX_MAP_HOST- This flag was deprecated as of CUDA 11.0 and it no longer has any effect.All contexts as of CUDA 3.2 behave as though the flag is enabled.
CTX_LMEM_RESIZE_TO_MAX- Keep local memory allocation after launchCTX_FLAGS_MASK
- See Also:
-
CU_CTX_MAP_HOST
public static final int CU_CTX_MAP_HOSTContext creation flags. (CUctx_flags)Enum values:
CTX_SCHED_AUTO- Automatic schedulingCTX_SCHED_SPIN- Set spin as default schedulingCTX_SCHED_YIELD- Set yield as default schedulingCTX_SCHED_BLOCKING_SYNC- Set blocking synchronization as default schedulingCTX_BLOCKING_SYNC- Set blocking synchronization as default scheduling. This flag was deprecated as of CUDA 4.0 and was replaced withCTX_SCHED_BLOCKING_SYNC.CTX_SCHED_MASKCTX_MAP_HOST- This flag was deprecated as of CUDA 11.0 and it no longer has any effect.All contexts as of CUDA 3.2 behave as though the flag is enabled.
CTX_LMEM_RESIZE_TO_MAX- Keep local memory allocation after launchCTX_FLAGS_MASK
- See Also:
-
CU_CTX_LMEM_RESIZE_TO_MAX
public static final int CU_CTX_LMEM_RESIZE_TO_MAXContext creation flags. (CUctx_flags)Enum values:
CTX_SCHED_AUTO- Automatic schedulingCTX_SCHED_SPIN- Set spin as default schedulingCTX_SCHED_YIELD- Set yield as default schedulingCTX_SCHED_BLOCKING_SYNC- Set blocking synchronization as default schedulingCTX_BLOCKING_SYNC- Set blocking synchronization as default scheduling. This flag was deprecated as of CUDA 4.0 and was replaced withCTX_SCHED_BLOCKING_SYNC.CTX_SCHED_MASKCTX_MAP_HOST- This flag was deprecated as of CUDA 11.0 and it no longer has any effect.All contexts as of CUDA 3.2 behave as though the flag is enabled.
CTX_LMEM_RESIZE_TO_MAX- Keep local memory allocation after launchCTX_FLAGS_MASK
- See Also:
-
CU_CTX_FLAGS_MASK
public static final int CU_CTX_FLAGS_MASKContext creation flags. (CUctx_flags)Enum values:
CTX_SCHED_AUTO- Automatic schedulingCTX_SCHED_SPIN- Set spin as default schedulingCTX_SCHED_YIELD- Set yield as default schedulingCTX_SCHED_BLOCKING_SYNC- Set blocking synchronization as default schedulingCTX_BLOCKING_SYNC- Set blocking synchronization as default scheduling. This flag was deprecated as of CUDA 4.0 and was replaced withCTX_SCHED_BLOCKING_SYNC.CTX_SCHED_MASKCTX_MAP_HOST- This flag was deprecated as of CUDA 11.0 and it no longer has any effect.All contexts as of CUDA 3.2 behave as though the flag is enabled.
CTX_LMEM_RESIZE_TO_MAX- Keep local memory allocation after launchCTX_FLAGS_MASK
- See Also:
-
CU_STREAM_DEFAULT
public static final int CU_STREAM_DEFAULTStream creation flags. (CUstream_flags)Enum values:
STREAM_DEFAULT- Default stream flagSTREAM_NON_BLOCKING- Stream does not synchronize with stream 0 (theNULLstream)
- See Also:
-
CU_STREAM_NON_BLOCKING
public static final int CU_STREAM_NON_BLOCKINGStream creation flags. (CUstream_flags)Enum values:
STREAM_DEFAULT- Default stream flagSTREAM_NON_BLOCKING- Stream does not synchronize with stream 0 (theNULLstream)
- See Also:
-
CU_STREAM_LEGACY
public static final long CU_STREAM_LEGACYLegacy stream handle.Stream handle that can be passed as a
CUstreamto use an implicit stream with legacy synchronization behavior.- See Also:
-
CU_STREAM_PER_THREAD
public static final long CU_STREAM_PER_THREADPer-thread stream handle.Stream handle that can be passed as a
CUstreamto use an implicit stream with per-thread synchronization behavior.- See Also:
-
CU_EVENT_DEFAULT
public static final int CU_EVENT_DEFAULTEvent creation flags. (CUevent_flags)Enum values:
EVENT_DEFAULT- Default event flagEVENT_BLOCKING_SYNC- Event uses blocking synchronizationEVENT_DISABLE_TIMING- Event will not record timing dataEVENT_INTERPROCESS- Event is suitable for interprocess use.EVENT_DISABLE_TIMINGmust be set
- See Also:
-
CU_EVENT_BLOCKING_SYNC
public static final int CU_EVENT_BLOCKING_SYNCEvent creation flags. (CUevent_flags)Enum values:
EVENT_DEFAULT- Default event flagEVENT_BLOCKING_SYNC- Event uses blocking synchronizationEVENT_DISABLE_TIMING- Event will not record timing dataEVENT_INTERPROCESS- Event is suitable for interprocess use.EVENT_DISABLE_TIMINGmust be set
- See Also:
-
CU_EVENT_DISABLE_TIMING
public static final int CU_EVENT_DISABLE_TIMINGEvent creation flags. (CUevent_flags)Enum values:
EVENT_DEFAULT- Default event flagEVENT_BLOCKING_SYNC- Event uses blocking synchronizationEVENT_DISABLE_TIMING- Event will not record timing dataEVENT_INTERPROCESS- Event is suitable for interprocess use.EVENT_DISABLE_TIMINGmust be set
- See Also:
-
CU_EVENT_INTERPROCESS
public static final int CU_EVENT_INTERPROCESSEvent creation flags. (CUevent_flags)Enum values:
EVENT_DEFAULT- Default event flagEVENT_BLOCKING_SYNC- Event uses blocking synchronizationEVENT_DISABLE_TIMING- Event will not record timing dataEVENT_INTERPROCESS- Event is suitable for interprocess use.EVENT_DISABLE_TIMINGmust be set
- See Also:
-
CU_EVENT_RECORD_DEFAULT
public static final int CU_EVENT_RECORD_DEFAULTEvent record flags. (CUevent_record_flags)Enum values:
EVENT_RECORD_DEFAULT- Default event record flagEVENT_RECORD_EXTERNAL- When using stream capture, create an event record node instead of the default behavior.This flag is invalid when used outside of capture.
- See Also:
-
CU_EVENT_RECORD_EXTERNAL
public static final int CU_EVENT_RECORD_EXTERNALEvent record flags. (CUevent_record_flags)Enum values:
EVENT_RECORD_DEFAULT- Default event record flagEVENT_RECORD_EXTERNAL- When using stream capture, create an event record node instead of the default behavior.This flag is invalid when used outside of capture.
- See Also:
-
CU_EVENT_WAIT_DEFAULT
public static final int CU_EVENT_WAIT_DEFAULTEvent wait flags. (CUevent_wait_flags)Enum values:
EVENT_WAIT_DEFAULT- Default event wait flagEVENT_WAIT_EXTERNAL- When using stream capture, create an event wait node instead of the default behavior.This flag is invalid when used outside of capture.
- See Also:
-
CU_EVENT_WAIT_EXTERNAL
public static final int CU_EVENT_WAIT_EXTERNALEvent wait flags. (CUevent_wait_flags)Enum values:
EVENT_WAIT_DEFAULT- Default event wait flagEVENT_WAIT_EXTERNAL- When using stream capture, create an event wait node instead of the default behavior.This flag is invalid when used outside of capture.
- See Also:
-
CU_STREAM_WAIT_VALUE_GEQ
public static final int CU_STREAM_WAIT_VALUE_GEQFlags forStreamWaitValue32andStreamWaitValue64. (CUstreamWaitValue_flags)Enum values:
STREAM_WAIT_VALUE_GEQ- Wait until(int32_t)(*addr - value) >= 0(orint64_tfor 64 bit values). Note this is a cyclic comparison which ignores wraparound. (Default behavior.)STREAM_WAIT_VALUE_EQ- Wait until*addr == value.STREAM_WAIT_VALUE_AND- Wait until(*addr & value) != 0.STREAM_WAIT_VALUE_NOR- Wait until~(*addr | value) != 0. Support for this operation can be queried withDeviceGetAttributeandDEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR.STREAM_WAIT_VALUE_FLUSH- Follow the wait operation with a flush of outstanding remote writes.This means that, if a remote write operation is guaranteed to have reached the device before the wait can be satisfied, that write is guaranteed to be visible to downstream device work. The device is permitted to reorder remote writes internally. For example, this flag would be required if two remote writes arrive in a defined order, the wait is satisfied by the second write, and downstream work needs to observe the first write.
Support for this operation is restricted to selected platforms and can be queried with
CU_DEVICE_ATTRIBUTE_CAN_USE_WAIT_VALUE_FLUSH.
- See Also:
-
CU_STREAM_WAIT_VALUE_EQ
public static final int CU_STREAM_WAIT_VALUE_EQFlags forStreamWaitValue32andStreamWaitValue64. (CUstreamWaitValue_flags)Enum values:
STREAM_WAIT_VALUE_GEQ- Wait until(int32_t)(*addr - value) >= 0(orint64_tfor 64 bit values). Note this is a cyclic comparison which ignores wraparound. (Default behavior.)STREAM_WAIT_VALUE_EQ- Wait until*addr == value.STREAM_WAIT_VALUE_AND- Wait until(*addr & value) != 0.STREAM_WAIT_VALUE_NOR- Wait until~(*addr | value) != 0. Support for this operation can be queried withDeviceGetAttributeandDEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR.STREAM_WAIT_VALUE_FLUSH- Follow the wait operation with a flush of outstanding remote writes.This means that, if a remote write operation is guaranteed to have reached the device before the wait can be satisfied, that write is guaranteed to be visible to downstream device work. The device is permitted to reorder remote writes internally. For example, this flag would be required if two remote writes arrive in a defined order, the wait is satisfied by the second write, and downstream work needs to observe the first write.
Support for this operation is restricted to selected platforms and can be queried with
CU_DEVICE_ATTRIBUTE_CAN_USE_WAIT_VALUE_FLUSH.
- See Also:
-
CU_STREAM_WAIT_VALUE_AND
public static final int CU_STREAM_WAIT_VALUE_ANDFlags forStreamWaitValue32andStreamWaitValue64. (CUstreamWaitValue_flags)Enum values:
STREAM_WAIT_VALUE_GEQ- Wait until(int32_t)(*addr - value) >= 0(orint64_tfor 64 bit values). Note this is a cyclic comparison which ignores wraparound. (Default behavior.)STREAM_WAIT_VALUE_EQ- Wait until*addr == value.STREAM_WAIT_VALUE_AND- Wait until(*addr & value) != 0.STREAM_WAIT_VALUE_NOR- Wait until~(*addr | value) != 0. Support for this operation can be queried withDeviceGetAttributeandDEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR.STREAM_WAIT_VALUE_FLUSH- Follow the wait operation with a flush of outstanding remote writes.This means that, if a remote write operation is guaranteed to have reached the device before the wait can be satisfied, that write is guaranteed to be visible to downstream device work. The device is permitted to reorder remote writes internally. For example, this flag would be required if two remote writes arrive in a defined order, the wait is satisfied by the second write, and downstream work needs to observe the first write.
Support for this operation is restricted to selected platforms and can be queried with
CU_DEVICE_ATTRIBUTE_CAN_USE_WAIT_VALUE_FLUSH.
- See Also:
-
CU_STREAM_WAIT_VALUE_NOR
public static final int CU_STREAM_WAIT_VALUE_NORFlags forStreamWaitValue32andStreamWaitValue64. (CUstreamWaitValue_flags)Enum values:
STREAM_WAIT_VALUE_GEQ- Wait until(int32_t)(*addr - value) >= 0(orint64_tfor 64 bit values). Note this is a cyclic comparison which ignores wraparound. (Default behavior.)STREAM_WAIT_VALUE_EQ- Wait until*addr == value.STREAM_WAIT_VALUE_AND- Wait until(*addr & value) != 0.STREAM_WAIT_VALUE_NOR- Wait until~(*addr | value) != 0. Support for this operation can be queried withDeviceGetAttributeandDEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR.STREAM_WAIT_VALUE_FLUSH- Follow the wait operation with a flush of outstanding remote writes.This means that, if a remote write operation is guaranteed to have reached the device before the wait can be satisfied, that write is guaranteed to be visible to downstream device work. The device is permitted to reorder remote writes internally. For example, this flag would be required if two remote writes arrive in a defined order, the wait is satisfied by the second write, and downstream work needs to observe the first write.
Support for this operation is restricted to selected platforms and can be queried with
CU_DEVICE_ATTRIBUTE_CAN_USE_WAIT_VALUE_FLUSH.
- See Also:
-
CU_STREAM_WAIT_VALUE_FLUSH
public static final int CU_STREAM_WAIT_VALUE_FLUSHFlags forStreamWaitValue32andStreamWaitValue64. (CUstreamWaitValue_flags)Enum values:
STREAM_WAIT_VALUE_GEQ- Wait until(int32_t)(*addr - value) >= 0(orint64_tfor 64 bit values). Note this is a cyclic comparison which ignores wraparound. (Default behavior.)STREAM_WAIT_VALUE_EQ- Wait until*addr == value.STREAM_WAIT_VALUE_AND- Wait until(*addr & value) != 0.STREAM_WAIT_VALUE_NOR- Wait until~(*addr | value) != 0. Support for this operation can be queried withDeviceGetAttributeandDEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR.STREAM_WAIT_VALUE_FLUSH- Follow the wait operation with a flush of outstanding remote writes.This means that, if a remote write operation is guaranteed to have reached the device before the wait can be satisfied, that write is guaranteed to be visible to downstream device work. The device is permitted to reorder remote writes internally. For example, this flag would be required if two remote writes arrive in a defined order, the wait is satisfied by the second write, and downstream work needs to observe the first write.
Support for this operation is restricted to selected platforms and can be queried with
CU_DEVICE_ATTRIBUTE_CAN_USE_WAIT_VALUE_FLUSH.
- See Also:
-
CU_STREAM_WRITE_VALUE_DEFAULT
public static final int CU_STREAM_WRITE_VALUE_DEFAULTFlags forStreamWriteValue32. (CUstreamWriteValue_flags)Enum values:
STREAM_WRITE_VALUE_DEFAULT- Default behaviorSTREAM_WRITE_VALUE_NO_MEMORY_BARRIER- Permits the write to be reordered with writes which were issued before it, as a performance optimization.Normally,
StreamWriteValue32will provide a memory fence before the write, which has similar semantics to__threadfence_system()but is scoped to the stream rather than a CUDA thread.
- See Also:
-
CU_STREAM_WRITE_VALUE_NO_MEMORY_BARRIER
public static final int CU_STREAM_WRITE_VALUE_NO_MEMORY_BARRIERFlags forStreamWriteValue32. (CUstreamWriteValue_flags)Enum values:
STREAM_WRITE_VALUE_DEFAULT- Default behaviorSTREAM_WRITE_VALUE_NO_MEMORY_BARRIER- Permits the write to be reordered with writes which were issued before it, as a performance optimization.Normally,
StreamWriteValue32will provide a memory fence before the write, which has similar semantics to__threadfence_system()but is scoped to the stream rather than a CUDA thread.
- See Also:
-
CU_STREAM_MEM_OP_WAIT_VALUE_32
public static final int CU_STREAM_MEM_OP_WAIT_VALUE_32Operations forStreamBatchMemOp. (CUstreamBatchMemOpType)Enum values:
STREAM_MEM_OP_WAIT_VALUE_32- Represents aStreamWaitValue32operationSTREAM_MEM_OP_WRITE_VALUE_32- Represents aStreamWriteValue32operationSTREAM_MEM_OP_WAIT_VALUE_64- Represents aStreamWaitValue64operationSTREAM_MEM_OP_WRITE_VALUE_64- Represents aStreamWriteValue64operationSTREAM_MEM_OP_FLUSH_REMOTE_WRITES- This has the same effect asSTREAM_WAIT_VALUE_FLUSH, but as a standalone operation.
- See Also:
-
CU_STREAM_MEM_OP_WRITE_VALUE_32
public static final int CU_STREAM_MEM_OP_WRITE_VALUE_32Operations forStreamBatchMemOp. (CUstreamBatchMemOpType)Enum values:
STREAM_MEM_OP_WAIT_VALUE_32- Represents aStreamWaitValue32operationSTREAM_MEM_OP_WRITE_VALUE_32- Represents aStreamWriteValue32operationSTREAM_MEM_OP_WAIT_VALUE_64- Represents aStreamWaitValue64operationSTREAM_MEM_OP_WRITE_VALUE_64- Represents aStreamWriteValue64operationSTREAM_MEM_OP_FLUSH_REMOTE_WRITES- This has the same effect asSTREAM_WAIT_VALUE_FLUSH, but as a standalone operation.
- See Also:
-
CU_STREAM_MEM_OP_WAIT_VALUE_64
public static final int CU_STREAM_MEM_OP_WAIT_VALUE_64Operations forStreamBatchMemOp. (CUstreamBatchMemOpType)Enum values:
STREAM_MEM_OP_WAIT_VALUE_32- Represents aStreamWaitValue32operationSTREAM_MEM_OP_WRITE_VALUE_32- Represents aStreamWriteValue32operationSTREAM_MEM_OP_WAIT_VALUE_64- Represents aStreamWaitValue64operationSTREAM_MEM_OP_WRITE_VALUE_64- Represents aStreamWriteValue64operationSTREAM_MEM_OP_FLUSH_REMOTE_WRITES- This has the same effect asSTREAM_WAIT_VALUE_FLUSH, but as a standalone operation.
- See Also:
-
CU_STREAM_MEM_OP_WRITE_VALUE_64
public static final int CU_STREAM_MEM_OP_WRITE_VALUE_64Operations forStreamBatchMemOp. (CUstreamBatchMemOpType)Enum values:
STREAM_MEM_OP_WAIT_VALUE_32- Represents aStreamWaitValue32operationSTREAM_MEM_OP_WRITE_VALUE_32- Represents aStreamWriteValue32operationSTREAM_MEM_OP_WAIT_VALUE_64- Represents aStreamWaitValue64operationSTREAM_MEM_OP_WRITE_VALUE_64- Represents aStreamWriteValue64operationSTREAM_MEM_OP_FLUSH_REMOTE_WRITES- This has the same effect asSTREAM_WAIT_VALUE_FLUSH, but as a standalone operation.
- See Also:
-
CU_STREAM_MEM_OP_FLUSH_REMOTE_WRITES
public static final int CU_STREAM_MEM_OP_FLUSH_REMOTE_WRITESOperations forStreamBatchMemOp. (CUstreamBatchMemOpType)Enum values:
STREAM_MEM_OP_WAIT_VALUE_32- Represents aStreamWaitValue32operationSTREAM_MEM_OP_WRITE_VALUE_32- Represents aStreamWriteValue32operationSTREAM_MEM_OP_WAIT_VALUE_64- Represents aStreamWaitValue64operationSTREAM_MEM_OP_WRITE_VALUE_64- Represents aStreamWriteValue64operationSTREAM_MEM_OP_FLUSH_REMOTE_WRITES- This has the same effect asSTREAM_WAIT_VALUE_FLUSH, but as a standalone operation.
- See Also:
-
CU_OCCUPANCY_DEFAULT
public static final int CU_OCCUPANCY_DEFAULTOccupancy calculator flag. (CUoccupancy_flags)Enum values:
OCCUPANCY_DEFAULT- Default behaviorOCCUPANCY_DISABLE_CACHING_OVERRIDE- Assume global caching is enabled and cannot be automatically turned off
- See Also:
-
CU_OCCUPANCY_DISABLE_CACHING_OVERRIDE
public static final int CU_OCCUPANCY_DISABLE_CACHING_OVERRIDEOccupancy calculator flag. (CUoccupancy_flags)Enum values:
OCCUPANCY_DEFAULT- Default behaviorOCCUPANCY_DISABLE_CACHING_OVERRIDE- Assume global caching is enabled and cannot be automatically turned off
- See Also:
-
CU_STREAM_ADD_CAPTURE_DEPENDENCIES
public static final int CU_STREAM_ADD_CAPTURE_DEPENDENCIESFlags forStreamUpdateCaptureDependencies). (CUstreamUpdateCaptureDependencies_flags)Enum values:
STREAM_ADD_CAPTURE_DEPENDENCIES- Add new nodes to the dependency setSTREAM_SET_CAPTURE_DEPENDENCIES- Replace the dependency set with the new nodes
- See Also:
-
CU_STREAM_SET_CAPTURE_DEPENDENCIES
public static final int CU_STREAM_SET_CAPTURE_DEPENDENCIESFlags forStreamUpdateCaptureDependencies). (CUstreamUpdateCaptureDependencies_flags)Enum values:
STREAM_ADD_CAPTURE_DEPENDENCIES- Add new nodes to the dependency setSTREAM_SET_CAPTURE_DEPENDENCIES- Replace the dependency set with the new nodes
- See Also:
-
CU_AD_FORMAT_UNSIGNED_INT8
public static final int CU_AD_FORMAT_UNSIGNED_INT8Array formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_UNSIGNED_INT16
public static final int CU_AD_FORMAT_UNSIGNED_INT16Array formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_UNSIGNED_INT32
public static final int CU_AD_FORMAT_UNSIGNED_INT32Array formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_SIGNED_INT8
public static final int CU_AD_FORMAT_SIGNED_INT8Array formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_SIGNED_INT16
public static final int CU_AD_FORMAT_SIGNED_INT16Array formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_SIGNED_INT32
public static final int CU_AD_FORMAT_SIGNED_INT32Array formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_HALF
public static final int CU_AD_FORMAT_HALFArray formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_FLOAT
public static final int CU_AD_FORMAT_FLOATArray formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_NV12
public static final int CU_AD_FORMAT_NV12Array formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_UNORM_INT8X1
public static final int CU_AD_FORMAT_UNORM_INT8X1Array formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_UNORM_INT8X2
public static final int CU_AD_FORMAT_UNORM_INT8X2Array formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_UNORM_INT8X4
public static final int CU_AD_FORMAT_UNORM_INT8X4Array formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_UNORM_INT16X1
public static final int CU_AD_FORMAT_UNORM_INT16X1Array formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_UNORM_INT16X2
public static final int CU_AD_FORMAT_UNORM_INT16X2Array formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_UNORM_INT16X4
public static final int CU_AD_FORMAT_UNORM_INT16X4Array formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_SNORM_INT8X1
public static final int CU_AD_FORMAT_SNORM_INT8X1Array formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_SNORM_INT8X2
public static final int CU_AD_FORMAT_SNORM_INT8X2Array formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_SNORM_INT8X4
public static final int CU_AD_FORMAT_SNORM_INT8X4Array formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_SNORM_INT16X1
public static final int CU_AD_FORMAT_SNORM_INT16X1Array formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_SNORM_INT16X2
public static final int CU_AD_FORMAT_SNORM_INT16X2Array formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_SNORM_INT16X4
public static final int CU_AD_FORMAT_SNORM_INT16X4Array formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_BC1_UNORM
public static final int CU_AD_FORMAT_BC1_UNORMArray formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_BC1_UNORM_SRGB
public static final int CU_AD_FORMAT_BC1_UNORM_SRGBArray formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_BC2_UNORM
public static final int CU_AD_FORMAT_BC2_UNORMArray formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_BC2_UNORM_SRGB
public static final int CU_AD_FORMAT_BC2_UNORM_SRGBArray formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_BC3_UNORM
public static final int CU_AD_FORMAT_BC3_UNORMArray formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_BC3_UNORM_SRGB
public static final int CU_AD_FORMAT_BC3_UNORM_SRGBArray formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_BC4_UNORM
public static final int CU_AD_FORMAT_BC4_UNORMArray formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_BC4_SNORM
public static final int CU_AD_FORMAT_BC4_SNORMArray formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_BC5_UNORM
public static final int CU_AD_FORMAT_BC5_UNORMArray formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_BC5_SNORM
public static final int CU_AD_FORMAT_BC5_SNORMArray formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_BC6H_UF16
public static final int CU_AD_FORMAT_BC6H_UF16Array formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_BC6H_SF16
public static final int CU_AD_FORMAT_BC6H_SF16Array formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_BC7_UNORM
public static final int CU_AD_FORMAT_BC7_UNORMArray formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_AD_FORMAT_BC7_UNORM_SRGB
public static final int CU_AD_FORMAT_BC7_UNORM_SRGBArray formats. (CUarray_format)Enum values:
AD_FORMAT_UNSIGNED_INT8- Unsigned 8-bit integersAD_FORMAT_UNSIGNED_INT16- Unsigned 16-bit integersAD_FORMAT_UNSIGNED_INT32- Unsigned 32-bit integersAD_FORMAT_SIGNED_INT8- Signed 8-bit integersAD_FORMAT_SIGNED_INT16- Signed 16-bit integersAD_FORMAT_SIGNED_INT32- Signed 32-bit integersAD_FORMAT_HALF- 16-bit floating pointAD_FORMAT_FLOAT- 32-bit floating pointAD_FORMAT_NV12- 8-bit YUV planar format, with 4:2:0 samplingAD_FORMAT_UNORM_INT8X1- 1 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X2- 2 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT8X4- 4 channel unsigned 8-bit normalized integerAD_FORMAT_UNORM_INT16X1- 1 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X2- 2 channel unsigned 16-bit normalized integerAD_FORMAT_UNORM_INT16X4- 4 channel unsigned 16-bit normalized integerAD_FORMAT_SNORM_INT8X1- 1 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X2- 2 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT8X4- 4 channel signed 8-bit normalized integerAD_FORMAT_SNORM_INT16X1- 1 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X2- 2 channel signed 16-bit normalized integerAD_FORMAT_SNORM_INT16X4- 4 channel signed 16-bit normalized integerAD_FORMAT_BC1_UNORM- 4 channel unsigned normalized block-compressed (BC1 compression) formatAD_FORMAT_BC1_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encodingAD_FORMAT_BC2_UNORM- 4 channel unsigned normalized block-compressed (BC2 compression) formatAD_FORMAT_BC2_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encodingAD_FORMAT_BC3_UNORM- 4 channel unsigned normalized block-compressed (BC3 compression) formatAD_FORMAT_BC3_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encodingAD_FORMAT_BC4_UNORM- 1 channel unsigned normalized block-compressed (BC4 compression) formatAD_FORMAT_BC4_SNORM- 1 channel signed normalized block-compressed (BC4 compression) formatAD_FORMAT_BC5_UNORM- 2 channel unsigned normalized block-compressed (BC5 compression) formatAD_FORMAT_BC5_SNORM- 2 channel signed normalized block-compressed (BC5 compression) formatAD_FORMAT_BC6H_UF16- 3 channel unsigned half-float block-compressed (BC6H compression) formatAD_FORMAT_BC6H_SF16- 3 channel signed half-float block-compressed (BC6H compression) formatAD_FORMAT_BC7_UNORM- 4 channel unsigned normalized block-compressed (BC7 compression) formatAD_FORMAT_BC7_UNORM_SRGB- 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding
- See Also:
-
CU_TR_ADDRESS_MODE_WRAP
public static final int CU_TR_ADDRESS_MODE_WRAPTexture reference addressing modes. (CUaddress_mode)Enum values:
TR_ADDRESS_MODE_WRAP- Wrapping address modeTR_ADDRESS_MODE_CLAMP- Clamp to edge address modeTR_ADDRESS_MODE_MIRROR- Mirror address modeTR_ADDRESS_MODE_BORDER- Border address mode
- See Also:
-
CU_TR_ADDRESS_MODE_CLAMP
public static final int CU_TR_ADDRESS_MODE_CLAMPTexture reference addressing modes. (CUaddress_mode)Enum values:
TR_ADDRESS_MODE_WRAP- Wrapping address modeTR_ADDRESS_MODE_CLAMP- Clamp to edge address modeTR_ADDRESS_MODE_MIRROR- Mirror address modeTR_ADDRESS_MODE_BORDER- Border address mode
- See Also:
-
CU_TR_ADDRESS_MODE_MIRROR
public static final int CU_TR_ADDRESS_MODE_MIRRORTexture reference addressing modes. (CUaddress_mode)Enum values:
TR_ADDRESS_MODE_WRAP- Wrapping address modeTR_ADDRESS_MODE_CLAMP- Clamp to edge address modeTR_ADDRESS_MODE_MIRROR- Mirror address modeTR_ADDRESS_MODE_BORDER- Border address mode
- See Also:
-
CU_TR_ADDRESS_MODE_BORDER
public static final int CU_TR_ADDRESS_MODE_BORDERTexture reference addressing modes. (CUaddress_mode)Enum values:
TR_ADDRESS_MODE_WRAP- Wrapping address modeTR_ADDRESS_MODE_CLAMP- Clamp to edge address modeTR_ADDRESS_MODE_MIRROR- Mirror address modeTR_ADDRESS_MODE_BORDER- Border address mode
- See Also:
-
CU_TR_FILTER_MODE_POINT
public static final int CU_TR_FILTER_MODE_POINTTexture reference filtering modes. (CUfilter_mode)Enum values:
TR_FILTER_MODE_POINT- Point filter modeTR_FILTER_MODE_LINEAR- Linear filter mode
- See Also:
-
CU_TR_FILTER_MODE_LINEAR
public static final int CU_TR_FILTER_MODE_LINEARTexture reference filtering modes. (CUfilter_mode)Enum values:
TR_FILTER_MODE_POINT- Point filter modeTR_FILTER_MODE_LINEAR- Linear filter mode
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK
public static final int CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCKDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X
public static final int CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_XDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y
public static final int CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_YDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z
public static final int CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_ZDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_X
public static final int CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_XDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y
public static final int CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_YDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z
public static final int CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_ZDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
public static final int CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK
public static final int CU_DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCKDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY
public static final int CU_DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORYDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_WARP_SIZE
public static final int CU_DEVICE_ATTRIBUTE_WARP_SIZEDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAX_PITCH
public static final int CU_DEVICE_ATTRIBUTE_MAX_PITCHDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
public static final int CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK
public static final int CU_DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCKDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_CLOCK_RATE
public static final int CU_DEVICE_ATTRIBUTE_CLOCK_RATEDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT
public static final int CU_DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENTDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_GPU_OVERLAP
public static final int CU_DEVICE_ATTRIBUTE_GPU_OVERLAPDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT
public static final int CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNTDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT
public static final int CU_DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_INTEGRATED
public static final int CU_DEVICE_ATTRIBUTE_INTEGRATEDDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY
public static final int CU_DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORYDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_COMPUTE_MODE
public static final int CU_DEVICE_ATTRIBUTE_COMPUTE_MODEDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTHDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTHDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHTDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTHDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHTDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTHDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTHDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHTDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICESDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT
public static final int CU_DEVICE_ATTRIBUTE_SURFACE_ALIGNMENTDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_CONCURRENT_KERNELS
public static final int CU_DEVICE_ATTRIBUTE_CONCURRENT_KERNELSDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_ECC_ENABLED
public static final int CU_DEVICE_ATTRIBUTE_ECC_ENABLEDDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_PCI_BUS_ID
public static final int CU_DEVICE_ATTRIBUTE_PCI_BUS_IDDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_PCI_DEVICE_ID
public static final int CU_DEVICE_ATTRIBUTE_PCI_DEVICE_IDDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_TCC_DRIVER
public static final int CU_DEVICE_ATTRIBUTE_TCC_DRIVERDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE
public static final int CU_DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATEDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH
public static final int CU_DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTHDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_L2_CACHE_SIZE
public static final int CU_DEVICE_ATTRIBUTE_L2_CACHE_SIZEDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR
public static final int CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSORDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT
public static final int CU_DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNTDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING
public static final int CU_DEVICE_ATTRIBUTE_UNIFIED_ADDRESSINGDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTHDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERSDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER
public static final int CU_DEVICE_ATTRIBUTE_CAN_TEX2D_GATHERDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTHDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHTDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATEDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATEDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATEDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_PCI_DOMAIN_ID
public static final int CU_DEVICE_ATTRIBUTE_PCI_DOMAIN_IDDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT
public static final int CU_DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENTDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTHDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTHDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERSDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTHDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTHDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHTDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTHDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHTDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTHDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTHDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERSDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTHDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHTDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERSDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTHDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTHDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERSDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTHDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTHDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHTDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCHDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTHDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHTDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR
public static final int CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJORDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR
public static final int CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINORDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH
public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTHDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED
public static final int CU_DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTEDDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED
public static final int CU_DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTEDDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED
public static final int CU_DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTEDDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR
public static final int CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSORDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR
public static final int CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSORDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MANAGED_MEMORY
public static final int CU_DEVICE_ATTRIBUTE_MANAGED_MEMORYDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MULTI_GPU_BOARD
public static final int CU_DEVICE_ATTRIBUTE_MULTI_GPU_BOARDDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID
public static final int CU_DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_IDDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED
public static final int CU_DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTEDDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO
public static final int CU_DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIODevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS
public static final int CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESSDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS
public static final int CU_DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESSDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED
public static final int CU_DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTEDDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM
public static final int CU_DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEMDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS
public static final int CU_DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPSDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS
public static final int CU_DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPSDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR
public static final int CU_DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NORDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH
public static final int CU_DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCHDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH
public static final int CU_DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCHDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN
public static final int CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTINDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES
public static final int CU_DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITESDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED
public static final int CU_DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTEDDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES
public static final int CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLESDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST
public static final int CU_DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOSTDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED
public static final int CU_DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTEDDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
public static final int CU_DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED
public static final int CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTEDDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED
public static final int CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTEDDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED
public static final int CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTEDDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR
public static final int CU_DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSORDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED
public static final int CU_DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTEDDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE
public static final int CU_DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZEDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE
public static final int CU_DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZEDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED
public static final int CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTEDDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK
public static final int CU_DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCKDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED
public static final int CU_DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTEDDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED
public static final int CU_DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTEDDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED
public static final int CU_DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTEDDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED
public static final int CU_DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTEDDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED
public static final int CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTEDDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS
public static final int CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONSDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING
public static final int CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERINGDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES
public static final int CU_DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPESDevice properties. (CUdevice_attribute)Enum values:
DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK- Maximum number of threads per blockDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X- Maximum block dimension XDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y- Maximum block dimension YDEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z- Maximum block dimension ZDEVICE_ATTRIBUTE_MAX_GRID_DIM_X- Maximum grid dimension XDEVICE_ATTRIBUTE_MAX_GRID_DIM_Y- Maximum grid dimension YDEVICE_ATTRIBUTE_MAX_GRID_DIM_Z- Maximum grid dimension ZDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK- Maximum shared memory available per block in bytesDEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCKDEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY- Memory available on device for __constant__ variables in a CUDA C kernel in bytesDEVICE_ATTRIBUTE_WARP_SIZE- Warp size in threadsDEVICE_ATTRIBUTE_MAX_PITCH- Maximum pitch in bytes allowed by memory copiesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK- Maximum number of 32-bit registers available per blockDEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK- Deprecated, useDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCKDEVICE_ATTRIBUTE_CLOCK_RATE- Typical clock frequency in kilohertzDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT- Alignment requirement for texturesDEVICE_ATTRIBUTE_GPU_OVERLAP- Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use insteadDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT- Number of multiprocessors on deviceDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT- Specifies whether there is a run time limit on kernelsDEVICE_ATTRIBUTE_INTEGRATED- Device is integrated with host memoryDEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY- Device can map host memory into CUDA address spaceDEVICE_ATTRIBUTE_COMPUTE_MODE- Compute mode (SeeCUcomputemodefor details)DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH- Maximum 1D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH- Maximum 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT- Maximum 2D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH- Maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT- Maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH- Maximum 3D texture depthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH- Maximum 2D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT- Maximum 2D layered texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS- Maximum layers in a 2D layered textureDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTHDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHTDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES- Deprecated, useDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERSDEVICE_ATTRIBUTE_SURFACE_ALIGNMENT- Alignment requirement for surfacesDEVICE_ATTRIBUTE_CONCURRENT_KERNELS- Device can possibly execute multiple kernels concurrentlyDEVICE_ATTRIBUTE_ECC_ENABLED- Device has ECC support enabledDEVICE_ATTRIBUTE_PCI_BUS_ID- PCI bus ID of the deviceDEVICE_ATTRIBUTE_PCI_DEVICE_ID- PCI device ID of the deviceDEVICE_ATTRIBUTE_TCC_DRIVER- Device is using TCC driver modelDEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE- Peak memory clock frequency in kilohertzDEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH- Global memory bus width in bitsDEVICE_ATTRIBUTE_L2_CACHE_SIZE- Size of L2 cache in bytesDEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR- Maximum resident threads per multiprocessorDEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT- Number of asynchronous enginesDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING- Device shares a unified address space with the hostDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH- Maximum 1D layered texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS- Maximum layers in a 1D layered textureDEVICE_ATTRIBUTE_CAN_TEX2D_GATHER- Deprecated, do not use.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH- Maximum 2D texture width ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT- Maximum 2D texture height ifCUDA_ARRAY3D_TEXTURE_GATHERis setDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE- Alternate maximum 3D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE- Alternate maximum 3D texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE- Alternate maximum 3D texture depthDEVICE_ATTRIBUTE_PCI_DOMAIN_ID- PCI domain ID of the deviceDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT- Pitch alignment requirement for texturesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH- Maximum cubemap texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered texture width/heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered textureDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH- Maximum 1D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH- Maximum 2D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT- Maximum 2D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH- Maximum 3D surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT- Maximum 3D surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH- Maximum 3D surface depthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH- Maximum 1D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS- Maximum layers in a 1D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH- Maximum 2D layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT- Maximum 2D layered surface heightDEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS- Maximum layers in a 2D layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH- Maximum cubemap surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH- Maximum cubemap layered surface widthDEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS- Maximum layers in a cubemap layered surfaceDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH- Deprecated, do not use. UsecudaDeviceGetTexture1DLinearMaxWidth()orDeviceGetTexture1DLinearMaxWidthinstead.DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH- Maximum 2D linear texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT- Maximum 2D linear texture heightDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH- Maximum 2D linear texture pitch in bytesDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH- Maximum mipmapped 2D texture widthDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT- Maximum mipmapped 2D texture heightDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR- Major compute capability version numberDEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR- Minor compute capability version numberDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH- Maximum mipmapped 1D texture widthDEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED- Device supports stream prioritiesDEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED- Device supports caching globals in L1DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED- Device supports caching locals in L1DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR- Maximum shared memory available per multiprocessor in bytesDEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR- Maximum number of 32-bit registers available per multiprocessorDEVICE_ATTRIBUTE_MANAGED_MEMORY- Device can allocate managed memory on this systemDEVICE_ATTRIBUTE_MULTI_GPU_BOARD- Device is on a multi-GPU boardDEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID- Unique id for a group of devices on the same multi-GPU boardDEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED- Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO- Ratio of single precision performance (in floating-point operations per second) to double precision performanceDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS- Device supports coherently accessing pageable memory without calling cudaHostRegister on itDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS- Device can coherently access managed memory concurrently with the CPUDEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED- Device supports compute preemption.DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM- Device can access host registered memory at the same virtual address as the CPUDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS-StreamBatchMemOpand related APIs are supported.DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS- 64-bit operations are supported inStreamBatchMemOpand related APIs.DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR-STREAM_WAIT_VALUE_NORis supported.DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH- Device supports launching cooperative kernels viaLaunchCooperativeKernelDEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH- Deprecated,LaunchCooperativeKernelMultiDeviceis deprecated.DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN- Maximum optin shared memory per blockDEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOp are supported on the device. SeeCUDA_MEMOPfor additional details.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED- Device supports host memory registration viacudaHostRegister().DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES- Device accesses pageable memory via the host's page tables.DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST- The host can directly access managed memory on the device without migration.DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED- Deprecated, UseDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTEDDEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED- Device supports virtual memory management APIs likeMemAddressReserve,MemCreate,MemMapand related APIsDEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED- Device supports exporting memory to a posix file descriptor withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 NT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED- Device supports exporting memory to a Win32 KMT handle withMemExportToShareableHandle, if requested viaMemCreateDEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR- Maximum number of blocks per multiprocessorDEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED- Device supports compression of memoryDEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE- Maximum L2 persisting lines capacity setting in bytes.DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE- Maximum value ofCUaccessPolicyWindow{@code num_bytes}.DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED- Device supports specifying the GPUDirect RDMA flag withMemCreateDEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK- Shared memory reserved by CUDA driver per block in bytesDEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED- Device supports sparse CUDA arrays and sparse CUDA mipmapped arraysDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED- Device supports using theMemHostRegisterflagMEMHOSTREGISTER_READ_ONLYto register memory that must be mapped as read-only to the GPUDEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED- External timeline semaphore interop is supported on the deviceDEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED- Device supports using theMemAllocAsyncandcuMemPool*family of APIsDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED- Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS- The returned attribute shall be interpreted as a bitmask, where the individual bits are described by theCUflushGPUDirectRDMAWritesOptionsenumDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING- GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. SeeCUGPUDirectRDMAWritesOrderingfor the numerical values returned here.DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES- Handle types supported with mempool based IPC
- See Also:
-
CU_POINTER_ATTRIBUTE_CONTEXT
public static final int CU_POINTER_ATTRIBUTE_CONTEXTPointer information. (CUpointer_attribute)Enum values:
POINTER_ATTRIBUTE_CONTEXT- TheCUcontexton which a pointer was allocated or registeredPOINTER_ATTRIBUTE_MEMORY_TYPE- TheCUmemorytypedescribing the physical location of a pointerPOINTER_ATTRIBUTE_DEVICE_POINTER- The address at which a pointer's memory may be accessed on the devicePOINTER_ATTRIBUTE_HOST_POINTER- The address at which a pointer's memory may be accessed on the hostPOINTER_ATTRIBUTE_P2P_TOKENS- A pair of tokens for use with thenv-p2p.hLinux kernel interfacePOINTER_ATTRIBUTE_SYNC_MEMOPS- Synchronize every synchronous memory operation initiated on this regionPOINTER_ATTRIBUTE_BUFFER_ID- A process-wide unique ID for an allocated memory regionPOINTER_ATTRIBUTE_IS_MANAGED- Indicates if the pointer points to managed memoryPOINTER_ATTRIBUTE_DEVICE_ORDINAL- A device ordinal of a device on which a pointer was allocated or registeredPOINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE- 1 if this pointer maps to an allocation that is suitable forcudaIpcGetMemHandle(), 0 otherwisePOINTER_ATTRIBUTE_RANGE_START_ADDR- Starting address for this requested pointerPOINTER_ATTRIBUTE_RANGE_SIZE- Size of the address range for this requested pointerPOINTER_ATTRIBUTE_MAPPED- 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwisePOINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES- Bitmask of allowedCUmemAllocationHandleTypefor this allocationPOINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE- 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA APIPOINTER_ATTRIBUTE_ACCESS_FLAGS- Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer givenPOINTER_ATTRIBUTE_MEMPOOL_HANDLE- Returns themempool handle for the allocation if it was allocated from amempool. Otherwise returnsNULL.
- See Also:
-
CU_POINTER_ATTRIBUTE_MEMORY_TYPE
public static final int CU_POINTER_ATTRIBUTE_MEMORY_TYPEPointer information. (CUpointer_attribute)Enum values:
POINTER_ATTRIBUTE_CONTEXT- TheCUcontexton which a pointer was allocated or registeredPOINTER_ATTRIBUTE_MEMORY_TYPE- TheCUmemorytypedescribing the physical location of a pointerPOINTER_ATTRIBUTE_DEVICE_POINTER- The address at which a pointer's memory may be accessed on the devicePOINTER_ATTRIBUTE_HOST_POINTER- The address at which a pointer's memory may be accessed on the hostPOINTER_ATTRIBUTE_P2P_TOKENS- A pair of tokens for use with thenv-p2p.hLinux kernel interfacePOINTER_ATTRIBUTE_SYNC_MEMOPS- Synchronize every synchronous memory operation initiated on this regionPOINTER_ATTRIBUTE_BUFFER_ID- A process-wide unique ID for an allocated memory regionPOINTER_ATTRIBUTE_IS_MANAGED- Indicates if the pointer points to managed memoryPOINTER_ATTRIBUTE_DEVICE_ORDINAL- A device ordinal of a device on which a pointer was allocated or registeredPOINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE- 1 if this pointer maps to an allocation that is suitable forcudaIpcGetMemHandle(), 0 otherwisePOINTER_ATTRIBUTE_RANGE_START_ADDR- Starting address for this requested pointerPOINTER_ATTRIBUTE_RANGE_SIZE- Size of the address range for this requested pointerPOINTER_ATTRIBUTE_MAPPED- 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwisePOINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES- Bitmask of allowedCUmemAllocationHandleTypefor this allocationPOINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE- 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA APIPOINTER_ATTRIBUTE_ACCESS_FLAGS- Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer givenPOINTER_ATTRIBUTE_MEMPOOL_HANDLE- Returns themempool handle for the allocation if it was allocated from amempool. Otherwise returnsNULL.
- See Also:
-
CU_POINTER_ATTRIBUTE_DEVICE_POINTER
public static final int CU_POINTER_ATTRIBUTE_DEVICE_POINTERPointer information. (CUpointer_attribute)Enum values:
POINTER_ATTRIBUTE_CONTEXT- TheCUcontexton which a pointer was allocated or registeredPOINTER_ATTRIBUTE_MEMORY_TYPE- TheCUmemorytypedescribing the physical location of a pointerPOINTER_ATTRIBUTE_DEVICE_POINTER- The address at which a pointer's memory may be accessed on the devicePOINTER_ATTRIBUTE_HOST_POINTER- The address at which a pointer's memory may be accessed on the hostPOINTER_ATTRIBUTE_P2P_TOKENS- A pair of tokens for use with thenv-p2p.hLinux kernel interfacePOINTER_ATTRIBUTE_SYNC_MEMOPS- Synchronize every synchronous memory operation initiated on this regionPOINTER_ATTRIBUTE_BUFFER_ID- A process-wide unique ID for an allocated memory regionPOINTER_ATTRIBUTE_IS_MANAGED- Indicates if the pointer points to managed memoryPOINTER_ATTRIBUTE_DEVICE_ORDINAL- A device ordinal of a device on which a pointer was allocated or registeredPOINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE- 1 if this pointer maps to an allocation that is suitable forcudaIpcGetMemHandle(), 0 otherwisePOINTER_ATTRIBUTE_RANGE_START_ADDR- Starting address for this requested pointerPOINTER_ATTRIBUTE_RANGE_SIZE- Size of the address range for this requested pointerPOINTER_ATTRIBUTE_MAPPED- 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwisePOINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES- Bitmask of allowedCUmemAllocationHandleTypefor this allocationPOINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE- 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA APIPOINTER_ATTRIBUTE_ACCESS_FLAGS- Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer givenPOINTER_ATTRIBUTE_MEMPOOL_HANDLE- Returns themempool handle for the allocation if it was allocated from amempool. Otherwise returnsNULL.
- See Also:
-
CU_POINTER_ATTRIBUTE_HOST_POINTER
public static final int CU_POINTER_ATTRIBUTE_HOST_POINTERPointer information. (CUpointer_attribute)Enum values:
POINTER_ATTRIBUTE_CONTEXT- TheCUcontexton which a pointer was allocated or registeredPOINTER_ATTRIBUTE_MEMORY_TYPE- TheCUmemorytypedescribing the physical location of a pointerPOINTER_ATTRIBUTE_DEVICE_POINTER- The address at which a pointer's memory may be accessed on the devicePOINTER_ATTRIBUTE_HOST_POINTER- The address at which a pointer's memory may be accessed on the hostPOINTER_ATTRIBUTE_P2P_TOKENS- A pair of tokens for use with thenv-p2p.hLinux kernel interfacePOINTER_ATTRIBUTE_SYNC_MEMOPS- Synchronize every synchronous memory operation initiated on this regionPOINTER_ATTRIBUTE_BUFFER_ID- A process-wide unique ID for an allocated memory regionPOINTER_ATTRIBUTE_IS_MANAGED- Indicates if the pointer points to managed memoryPOINTER_ATTRIBUTE_DEVICE_ORDINAL- A device ordinal of a device on which a pointer was allocated or registeredPOINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE- 1 if this pointer maps to an allocation that is suitable forcudaIpcGetMemHandle(), 0 otherwisePOINTER_ATTRIBUTE_RANGE_START_ADDR- Starting address for this requested pointerPOINTER_ATTRIBUTE_RANGE_SIZE- Size of the address range for this requested pointerPOINTER_ATTRIBUTE_MAPPED- 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwisePOINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES- Bitmask of allowedCUmemAllocationHandleTypefor this allocationPOINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE- 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA APIPOINTER_ATTRIBUTE_ACCESS_FLAGS- Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer givenPOINTER_ATTRIBUTE_MEMPOOL_HANDLE- Returns themempool handle for the allocation if it was allocated from amempool. Otherwise returnsNULL.
- See Also:
-
CU_POINTER_ATTRIBUTE_P2P_TOKENS
public static final int CU_POINTER_ATTRIBUTE_P2P_TOKENSPointer information. (CUpointer_attribute)Enum values:
POINTER_ATTRIBUTE_CONTEXT- TheCUcontexton which a pointer was allocated or registeredPOINTER_ATTRIBUTE_MEMORY_TYPE- TheCUmemorytypedescribing the physical location of a pointerPOINTER_ATTRIBUTE_DEVICE_POINTER- The address at which a pointer's memory may be accessed on the devicePOINTER_ATTRIBUTE_HOST_POINTER- The address at which a pointer's memory may be accessed on the hostPOINTER_ATTRIBUTE_P2P_TOKENS- A pair of tokens for use with thenv-p2p.hLinux kernel interfacePOINTER_ATTRIBUTE_SYNC_MEMOPS- Synchronize every synchronous memory operation initiated on this regionPOINTER_ATTRIBUTE_BUFFER_ID- A process-wide unique ID for an allocated memory regionPOINTER_ATTRIBUTE_IS_MANAGED- Indicates if the pointer points to managed memoryPOINTER_ATTRIBUTE_DEVICE_ORDINAL- A device ordinal of a device on which a pointer was allocated or registeredPOINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE- 1 if this pointer maps to an allocation that is suitable forcudaIpcGetMemHandle(), 0 otherwisePOINTER_ATTRIBUTE_RANGE_START_ADDR- Starting address for this requested pointerPOINTER_ATTRIBUTE_RANGE_SIZE- Size of the address range for this requested pointerPOINTER_ATTRIBUTE_MAPPED- 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwisePOINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES- Bitmask of allowedCUmemAllocationHandleTypefor this allocationPOINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE- 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA APIPOINTER_ATTRIBUTE_ACCESS_FLAGS- Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer givenPOINTER_ATTRIBUTE_MEMPOOL_HANDLE- Returns themempool handle for the allocation if it was allocated from amempool. Otherwise returnsNULL.
- See Also:
-
CU_POINTER_ATTRIBUTE_SYNC_MEMOPS
public static final int CU_POINTER_ATTRIBUTE_SYNC_MEMOPSPointer information. (CUpointer_attribute)Enum values:
POINTER_ATTRIBUTE_CONTEXT- TheCUcontexton which a pointer was allocated or registeredPOINTER_ATTRIBUTE_MEMORY_TYPE- TheCUmemorytypedescribing the physical location of a pointerPOINTER_ATTRIBUTE_DEVICE_POINTER- The address at which a pointer's memory may be accessed on the devicePOINTER_ATTRIBUTE_HOST_POINTER- The address at which a pointer's memory may be accessed on the hostPOINTER_ATTRIBUTE_P2P_TOKENS- A pair of tokens for use with thenv-p2p.hLinux kernel interfacePOINTER_ATTRIBUTE_SYNC_MEMOPS- Synchronize every synchronous memory operation initiated on this regionPOINTER_ATTRIBUTE_BUFFER_ID- A process-wide unique ID for an allocated memory regionPOINTER_ATTRIBUTE_IS_MANAGED- Indicates if the pointer points to managed memoryPOINTER_ATTRIBUTE_DEVICE_ORDINAL- A device ordinal of a device on which a pointer was allocated or registeredPOINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE- 1 if this pointer maps to an allocation that is suitable forcudaIpcGetMemHandle(), 0 otherwisePOINTER_ATTRIBUTE_RANGE_START_ADDR- Starting address for this requested pointerPOINTER_ATTRIBUTE_RANGE_SIZE- Size of the address range for this requested pointerPOINTER_ATTRIBUTE_MAPPED- 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwisePOINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES- Bitmask of allowedCUmemAllocationHandleTypefor this allocationPOINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE- 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA APIPOINTER_ATTRIBUTE_ACCESS_FLAGS- Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer givenPOINTER_ATTRIBUTE_MEMPOOL_HANDLE- Returns themempool handle for the allocation if it was allocated from amempool. Otherwise returnsNULL.
- See Also:
-
CU_POINTER_ATTRIBUTE_BUFFER_ID
public static final int CU_POINTER_ATTRIBUTE_BUFFER_IDPointer information. (CUpointer_attribute)Enum values:
POINTER_ATTRIBUTE_CONTEXT- TheCUcontexton which a pointer was allocated or registeredPOINTER_ATTRIBUTE_MEMORY_TYPE- TheCUmemorytypedescribing the physical location of a pointerPOINTER_ATTRIBUTE_DEVICE_POINTER- The address at which a pointer's memory may be accessed on the devicePOINTER_ATTRIBUTE_HOST_POINTER- The address at which a pointer's memory may be accessed on the hostPOINTER_ATTRIBUTE_P2P_TOKENS- A pair of tokens for use with thenv-p2p.hLinux kernel interfacePOINTER_ATTRIBUTE_SYNC_MEMOPS- Synchronize every synchronous memory operation initiated on this regionPOINTER_ATTRIBUTE_BUFFER_ID- A process-wide unique ID for an allocated memory regionPOINTER_ATTRIBUTE_IS_MANAGED- Indicates if the pointer points to managed memoryPOINTER_ATTRIBUTE_DEVICE_ORDINAL- A device ordinal of a device on which a pointer was allocated or registeredPOINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE- 1 if this pointer maps to an allocation that is suitable forcudaIpcGetMemHandle(), 0 otherwisePOINTER_ATTRIBUTE_RANGE_START_ADDR- Starting address for this requested pointerPOINTER_ATTRIBUTE_RANGE_SIZE- Size of the address range for this requested pointerPOINTER_ATTRIBUTE_MAPPED- 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwisePOINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES- Bitmask of allowedCUmemAllocationHandleTypefor this allocationPOINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE- 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA APIPOINTER_ATTRIBUTE_ACCESS_FLAGS- Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer givenPOINTER_ATTRIBUTE_MEMPOOL_HANDLE- Returns themempool handle for the allocation if it was allocated from amempool. Otherwise returnsNULL.
- See Also:
-
CU_POINTER_ATTRIBUTE_IS_MANAGED
public static final int CU_POINTER_ATTRIBUTE_IS_MANAGEDPointer information. (CUpointer_attribute)Enum values:
POINTER_ATTRIBUTE_CONTEXT- TheCUcontexton which a pointer was allocated or registeredPOINTER_ATTRIBUTE_MEMORY_TYPE- TheCUmemorytypedescribing the physical location of a pointerPOINTER_ATTRIBUTE_DEVICE_POINTER- The address at which a pointer's memory may be accessed on the devicePOINTER_ATTRIBUTE_HOST_POINTER- The address at which a pointer's memory may be accessed on the hostPOINTER_ATTRIBUTE_P2P_TOKENS- A pair of tokens for use with thenv-p2p.hLinux kernel interfacePOINTER_ATTRIBUTE_SYNC_MEMOPS- Synchronize every synchronous memory operation initiated on this regionPOINTER_ATTRIBUTE_BUFFER_ID- A process-wide unique ID for an allocated memory regionPOINTER_ATTRIBUTE_IS_MANAGED- Indicates if the pointer points to managed memoryPOINTER_ATTRIBUTE_DEVICE_ORDINAL- A device ordinal of a device on which a pointer was allocated or registeredPOINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE- 1 if this pointer maps to an allocation that is suitable forcudaIpcGetMemHandle(), 0 otherwisePOINTER_ATTRIBUTE_RANGE_START_ADDR- Starting address for this requested pointerPOINTER_ATTRIBUTE_RANGE_SIZE- Size of the address range for this requested pointerPOINTER_ATTRIBUTE_MAPPED- 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwisePOINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES- Bitmask of allowedCUmemAllocationHandleTypefor this allocationPOINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE- 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA APIPOINTER_ATTRIBUTE_ACCESS_FLAGS- Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer givenPOINTER_ATTRIBUTE_MEMPOOL_HANDLE- Returns themempool handle for the allocation if it was allocated from amempool. Otherwise returnsNULL.
- See Also:
-
CU_POINTER_ATTRIBUTE_DEVICE_ORDINAL
public static final int CU_POINTER_ATTRIBUTE_DEVICE_ORDINALPointer information. (CUpointer_attribute)Enum values:
POINTER_ATTRIBUTE_CONTEXT- TheCUcontexton which a pointer was allocated or registeredPOINTER_ATTRIBUTE_MEMORY_TYPE- TheCUmemorytypedescribing the physical location of a pointerPOINTER_ATTRIBUTE_DEVICE_POINTER- The address at which a pointer's memory may be accessed on the devicePOINTER_ATTRIBUTE_HOST_POINTER- The address at which a pointer's memory may be accessed on the hostPOINTER_ATTRIBUTE_P2P_TOKENS- A pair of tokens for use with thenv-p2p.hLinux kernel interfacePOINTER_ATTRIBUTE_SYNC_MEMOPS- Synchronize every synchronous memory operation initiated on this regionPOINTER_ATTRIBUTE_BUFFER_ID- A process-wide unique ID for an allocated memory regionPOINTER_ATTRIBUTE_IS_MANAGED- Indicates if the pointer points to managed memoryPOINTER_ATTRIBUTE_DEVICE_ORDINAL- A device ordinal of a device on which a pointer was allocated or registeredPOINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE- 1 if this pointer maps to an allocation that is suitable forcudaIpcGetMemHandle(), 0 otherwisePOINTER_ATTRIBUTE_RANGE_START_ADDR- Starting address for this requested pointerPOINTER_ATTRIBUTE_RANGE_SIZE- Size of the address range for this requested pointerPOINTER_ATTRIBUTE_MAPPED- 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwisePOINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES- Bitmask of allowedCUmemAllocationHandleTypefor this allocationPOINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE- 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA APIPOINTER_ATTRIBUTE_ACCESS_FLAGS- Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer givenPOINTER_ATTRIBUTE_MEMPOOL_HANDLE- Returns themempool handle for the allocation if it was allocated from amempool. Otherwise returnsNULL.
- See Also:
-
CU_POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE
public static final int CU_POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLEPointer information. (CUpointer_attribute)Enum values:
POINTER_ATTRIBUTE_CONTEXT- TheCUcontexton which a pointer was allocated or registeredPOINTER_ATTRIBUTE_MEMORY_TYPE- TheCUmemorytypedescribing the physical location of a pointerPOINTER_ATTRIBUTE_DEVICE_POINTER- The address at which a pointer's memory may be accessed on the devicePOINTER_ATTRIBUTE_HOST_POINTER- The address at which a pointer's memory may be accessed on the hostPOINTER_ATTRIBUTE_P2P_TOKENS- A pair of tokens for use with thenv-p2p.hLinux kernel interfacePOINTER_ATTRIBUTE_SYNC_MEMOPS- Synchronize every synchronous memory operation initiated on this regionPOINTER_ATTRIBUTE_BUFFER_ID- A process-wide unique ID for an allocated memory regionPOINTER_ATTRIBUTE_IS_MANAGED- Indicates if the pointer points to managed memoryPOINTER_ATTRIBUTE_DEVICE_ORDINAL- A device ordinal of a device on which a pointer was allocated or registeredPOINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE- 1 if this pointer maps to an allocation that is suitable forcudaIpcGetMemHandle(), 0 otherwisePOINTER_ATTRIBUTE_RANGE_START_ADDR- Starting address for this requested pointerPOINTER_ATTRIBUTE_RANGE_SIZE- Size of the address range for this requested pointerPOINTER_ATTRIBUTE_MAPPED- 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwisePOINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES- Bitmask of allowedCUmemAllocationHandleTypefor this allocationPOINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE- 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA APIPOINTER_ATTRIBUTE_ACCESS_FLAGS- Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer givenPOINTER_ATTRIBUTE_MEMPOOL_HANDLE- Returns themempool handle for the allocation if it was allocated from amempool. Otherwise returnsNULL.
- See Also:
-
CU_POINTER_ATTRIBUTE_RANGE_START_ADDR
public static final int CU_POINTER_ATTRIBUTE_RANGE_START_ADDRPointer information. (CUpointer_attribute)Enum values:
POINTER_ATTRIBUTE_CONTEXT- TheCUcontexton which a pointer was allocated or registeredPOINTER_ATTRIBUTE_MEMORY_TYPE- TheCUmemorytypedescribing the physical location of a pointerPOINTER_ATTRIBUTE_DEVICE_POINTER- The address at which a pointer's memory may be accessed on the devicePOINTER_ATTRIBUTE_HOST_POINTER- The address at which a pointer's memory may be accessed on the hostPOINTER_ATTRIBUTE_P2P_TOKENS- A pair of tokens for use with thenv-p2p.hLinux kernel interfacePOINTER_ATTRIBUTE_SYNC_MEMOPS- Synchronize every synchronous memory operation initiated on this regionPOINTER_ATTRIBUTE_BUFFER_ID- A process-wide unique ID for an allocated memory regionPOINTER_ATTRIBUTE_IS_MANAGED- Indicates if the pointer points to managed memoryPOINTER_ATTRIBUTE_DEVICE_ORDINAL- A device ordinal of a device on which a pointer was allocated or registeredPOINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE- 1 if this pointer maps to an allocation that is suitable forcudaIpcGetMemHandle(), 0 otherwisePOINTER_ATTRIBUTE_RANGE_START_ADDR- Starting address for this requested pointerPOINTER_ATTRIBUTE_RANGE_SIZE- Size of the address range for this requested pointerPOINTER_ATTRIBUTE_MAPPED- 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwisePOINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES- Bitmask of allowedCUmemAllocationHandleTypefor this allocationPOINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE- 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA APIPOINTER_ATTRIBUTE_ACCESS_FLAGS- Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer givenPOINTER_ATTRIBUTE_MEMPOOL_HANDLE- Returns themempool handle for the allocation if it was allocated from amempool. Otherwise returnsNULL.
- See Also:
-
CU_POINTER_ATTRIBUTE_RANGE_SIZE
public static final int CU_POINTER_ATTRIBUTE_RANGE_SIZEPointer information. (CUpointer_attribute)Enum values:
POINTER_ATTRIBUTE_CONTEXT- TheCUcontexton which a pointer was allocated or registeredPOINTER_ATTRIBUTE_MEMORY_TYPE- TheCUmemorytypedescribing the physical location of a pointerPOINTER_ATTRIBUTE_DEVICE_POINTER- The address at which a pointer's memory may be accessed on the devicePOINTER_ATTRIBUTE_HOST_POINTER- The address at which a pointer's memory may be accessed on the hostPOINTER_ATTRIBUTE_P2P_TOKENS- A pair of tokens for use with thenv-p2p.hLinux kernel interfacePOINTER_ATTRIBUTE_SYNC_MEMOPS- Synchronize every synchronous memory operation initiated on this regionPOINTER_ATTRIBUTE_BUFFER_ID- A process-wide unique ID for an allocated memory regionPOINTER_ATTRIBUTE_IS_MANAGED- Indicates if the pointer points to managed memoryPOINTER_ATTRIBUTE_DEVICE_ORDINAL- A device ordinal of a device on which a pointer was allocated or registeredPOINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE- 1 if this pointer maps to an allocation that is suitable forcudaIpcGetMemHandle(), 0 otherwisePOINTER_ATTRIBUTE_RANGE_START_ADDR- Starting address for this requested pointerPOINTER_ATTRIBUTE_RANGE_SIZE- Size of the address range for this requested pointerPOINTER_ATTRIBUTE_MAPPED- 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwisePOINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES- Bitmask of allowedCUmemAllocationHandleTypefor this allocationPOINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE- 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA APIPOINTER_ATTRIBUTE_ACCESS_FLAGS- Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer givenPOINTER_ATTRIBUTE_MEMPOOL_HANDLE- Returns themempool handle for the allocation if it was allocated from amempool. Otherwise returnsNULL.
- See Also:
-
CU_POINTER_ATTRIBUTE_MAPPED
public static final int CU_POINTER_ATTRIBUTE_MAPPEDPointer information. (CUpointer_attribute)Enum values:
POINTER_ATTRIBUTE_CONTEXT- TheCUcontexton which a pointer was allocated or registeredPOINTER_ATTRIBUTE_MEMORY_TYPE- TheCUmemorytypedescribing the physical location of a pointerPOINTER_ATTRIBUTE_DEVICE_POINTER- The address at which a pointer's memory may be accessed on the devicePOINTER_ATTRIBUTE_HOST_POINTER- The address at which a pointer's memory may be accessed on the hostPOINTER_ATTRIBUTE_P2P_TOKENS- A pair of tokens for use with thenv-p2p.hLinux kernel interfacePOINTER_ATTRIBUTE_SYNC_MEMOPS- Synchronize every synchronous memory operation initiated on this regionPOINTER_ATTRIBUTE_BUFFER_ID- A process-wide unique ID for an allocated memory regionPOINTER_ATTRIBUTE_IS_MANAGED- Indicates if the pointer points to managed memoryPOINTER_ATTRIBUTE_DEVICE_ORDINAL- A device ordinal of a device on which a pointer was allocated or registeredPOINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE- 1 if this pointer maps to an allocation that is suitable forcudaIpcGetMemHandle(), 0 otherwisePOINTER_ATTRIBUTE_RANGE_START_ADDR- Starting address for this requested pointerPOINTER_ATTRIBUTE_RANGE_SIZE- Size of the address range for this requested pointerPOINTER_ATTRIBUTE_MAPPED- 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwisePOINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES- Bitmask of allowedCUmemAllocationHandleTypefor this allocationPOINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE- 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA APIPOINTER_ATTRIBUTE_ACCESS_FLAGS- Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer givenPOINTER_ATTRIBUTE_MEMPOOL_HANDLE- Returns themempool handle for the allocation if it was allocated from amempool. Otherwise returnsNULL.
- See Also:
-
CU_POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES
public static final int CU_POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPESPointer information. (CUpointer_attribute)Enum values:
POINTER_ATTRIBUTE_CONTEXT- TheCUcontexton which a pointer was allocated or registeredPOINTER_ATTRIBUTE_MEMORY_TYPE- TheCUmemorytypedescribing the physical location of a pointerPOINTER_ATTRIBUTE_DEVICE_POINTER- The address at which a pointer's memory may be accessed on the devicePOINTER_ATTRIBUTE_HOST_POINTER- The address at which a pointer's memory may be accessed on the hostPOINTER_ATTRIBUTE_P2P_TOKENS- A pair of tokens for use with thenv-p2p.hLinux kernel interfacePOINTER_ATTRIBUTE_SYNC_MEMOPS- Synchronize every synchronous memory operation initiated on this regionPOINTER_ATTRIBUTE_BUFFER_ID- A process-wide unique ID for an allocated memory regionPOINTER_ATTRIBUTE_IS_MANAGED- Indicates if the pointer points to managed memoryPOINTER_ATTRIBUTE_DEVICE_ORDINAL- A device ordinal of a device on which a pointer was allocated or registeredPOINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE- 1 if this pointer maps to an allocation that is suitable forcudaIpcGetMemHandle(), 0 otherwisePOINTER_ATTRIBUTE_RANGE_START_ADDR- Starting address for this requested pointerPOINTER_ATTRIBUTE_RANGE_SIZE- Size of the address range for this requested pointerPOINTER_ATTRIBUTE_MAPPED- 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwisePOINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES- Bitmask of allowedCUmemAllocationHandleTypefor this allocationPOINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE- 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA APIPOINTER_ATTRIBUTE_ACCESS_FLAGS- Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer givenPOINTER_ATTRIBUTE_MEMPOOL_HANDLE- Returns themempool handle for the allocation if it was allocated from amempool. Otherwise returnsNULL.
- See Also:
-
CU_POINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE
public static final int CU_POINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLEPointer information. (CUpointer_attribute)Enum values:
POINTER_ATTRIBUTE_CONTEXT- TheCUcontexton which a pointer was allocated or registeredPOINTER_ATTRIBUTE_MEMORY_TYPE- TheCUmemorytypedescribing the physical location of a pointerPOINTER_ATTRIBUTE_DEVICE_POINTER- The address at which a pointer's memory may be accessed on the devicePOINTER_ATTRIBUTE_HOST_POINTER- The address at which a pointer's memory may be accessed on the hostPOINTER_ATTRIBUTE_P2P_TOKENS- A pair of tokens for use with thenv-p2p.hLinux kernel interfacePOINTER_ATTRIBUTE_SYNC_MEMOPS- Synchronize every synchronous memory operation initiated on this regionPOINTER_ATTRIBUTE_BUFFER_ID- A process-wide unique ID for an allocated memory regionPOINTER_ATTRIBUTE_IS_MANAGED- Indicates if the pointer points to managed memoryPOINTER_ATTRIBUTE_DEVICE_ORDINAL- A device ordinal of a device on which a pointer was allocated or registeredPOINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE- 1 if this pointer maps to an allocation that is suitable forcudaIpcGetMemHandle(), 0 otherwisePOINTER_ATTRIBUTE_RANGE_START_ADDR- Starting address for this requested pointerPOINTER_ATTRIBUTE_RANGE_SIZE- Size of the address range for this requested pointerPOINTER_ATTRIBUTE_MAPPED- 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwisePOINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES- Bitmask of allowedCUmemAllocationHandleTypefor this allocationPOINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE- 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA APIPOINTER_ATTRIBUTE_ACCESS_FLAGS- Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer givenPOINTER_ATTRIBUTE_MEMPOOL_HANDLE- Returns themempool handle for the allocation if it was allocated from amempool. Otherwise returnsNULL.
- See Also:
-
CU_POINTER_ATTRIBUTE_ACCESS_FLAGS
public static final int CU_POINTER_ATTRIBUTE_ACCESS_FLAGSPointer information. (CUpointer_attribute)Enum values:
POINTER_ATTRIBUTE_CONTEXT- TheCUcontexton which a pointer was allocated or registeredPOINTER_ATTRIBUTE_MEMORY_TYPE- TheCUmemorytypedescribing the physical location of a pointerPOINTER_ATTRIBUTE_DEVICE_POINTER- The address at which a pointer's memory may be accessed on the devicePOINTER_ATTRIBUTE_HOST_POINTER- The address at which a pointer's memory may be accessed on the hostPOINTER_ATTRIBUTE_P2P_TOKENS- A pair of tokens for use with thenv-p2p.hLinux kernel interfacePOINTER_ATTRIBUTE_SYNC_MEMOPS- Synchronize every synchronous memory operation initiated on this regionPOINTER_ATTRIBUTE_BUFFER_ID- A process-wide unique ID for an allocated memory regionPOINTER_ATTRIBUTE_IS_MANAGED- Indicates if the pointer points to managed memoryPOINTER_ATTRIBUTE_DEVICE_ORDINAL- A device ordinal of a device on which a pointer was allocated or registeredPOINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE- 1 if this pointer maps to an allocation that is suitable forcudaIpcGetMemHandle(), 0 otherwisePOINTER_ATTRIBUTE_RANGE_START_ADDR- Starting address for this requested pointerPOINTER_ATTRIBUTE_RANGE_SIZE- Size of the address range for this requested pointerPOINTER_ATTRIBUTE_MAPPED- 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwisePOINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES- Bitmask of allowedCUmemAllocationHandleTypefor this allocationPOINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE- 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA APIPOINTER_ATTRIBUTE_ACCESS_FLAGS- Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer givenPOINTER_ATTRIBUTE_MEMPOOL_HANDLE- Returns themempool handle for the allocation if it was allocated from amempool. Otherwise returnsNULL.
- See Also:
-
CU_POINTER_ATTRIBUTE_MEMPOOL_HANDLE
public static final int CU_POINTER_ATTRIBUTE_MEMPOOL_HANDLEPointer information. (CUpointer_attribute)Enum values:
POINTER_ATTRIBUTE_CONTEXT- TheCUcontexton which a pointer was allocated or registeredPOINTER_ATTRIBUTE_MEMORY_TYPE- TheCUmemorytypedescribing the physical location of a pointerPOINTER_ATTRIBUTE_DEVICE_POINTER- The address at which a pointer's memory may be accessed on the devicePOINTER_ATTRIBUTE_HOST_POINTER- The address at which a pointer's memory may be accessed on the hostPOINTER_ATTRIBUTE_P2P_TOKENS- A pair of tokens for use with thenv-p2p.hLinux kernel interfacePOINTER_ATTRIBUTE_SYNC_MEMOPS- Synchronize every synchronous memory operation initiated on this regionPOINTER_ATTRIBUTE_BUFFER_ID- A process-wide unique ID for an allocated memory regionPOINTER_ATTRIBUTE_IS_MANAGED- Indicates if the pointer points to managed memoryPOINTER_ATTRIBUTE_DEVICE_ORDINAL- A device ordinal of a device on which a pointer was allocated or registeredPOINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE- 1 if this pointer maps to an allocation that is suitable forcudaIpcGetMemHandle(), 0 otherwisePOINTER_ATTRIBUTE_RANGE_START_ADDR- Starting address for this requested pointerPOINTER_ATTRIBUTE_RANGE_SIZE- Size of the address range for this requested pointerPOINTER_ATTRIBUTE_MAPPED- 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwisePOINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES- Bitmask of allowedCUmemAllocationHandleTypefor this allocationPOINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE- 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA APIPOINTER_ATTRIBUTE_ACCESS_FLAGS- Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer givenPOINTER_ATTRIBUTE_MEMPOOL_HANDLE- Returns themempool handle for the allocation if it was allocated from amempool. Otherwise returnsNULL.
- See Also:
-
CU_FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK
public static final int CU_FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCKFunction properties. (CUfunction_attribute)Enum values:
FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK- The maximum number of threads per block, beyond which a launch of the function would fail. This number depends on both the function and the device on which the function is currently loaded.FUNC_ATTRIBUTE_SHARED_SIZE_BYTES- The size in bytes of statically-allocated shared memory required by this function. This does not include dynamically-allocated shared memory requested by the user at runtime.FUNC_ATTRIBUTE_CONST_SIZE_BYTES- The size in bytes of user-allocated constant memory required by this function.FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES- The size in bytes of local memory used by each thread of this function.FUNC_ATTRIBUTE_NUM_REGS- The number of registers used by each thread of this function.FUNC_ATTRIBUTE_PTX_VERSION- The PTX virtual architecture version for which the function was compiled.This value is the major PTX
version * 10 + the minor PTX version, so a PTX version 1.3 function would return the value 13. Note that this may return the undefined value of 0 for cubins compiled prior to CUDA 3.0.FUNC_ATTRIBUTE_BINARY_VERSION- The binary architecture version for which the function was compiled.This value is the
major binary version * 10 + the minor binary version, so a binary version 1.3 function would return the value 13. Note that this will return a value of 10 for legacy cubins that do not have a properly-encoded binary architecture version.FUNC_ATTRIBUTE_CACHE_MODE_CA- The attribute to indicate whether the function has been compiled with user specified option"-Xptxas --dlcm=ca"set.FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES- The maximum size in bytes of dynamically-allocated shared memory that can be used by this function.If the user-specified dynamic shared memory size is larger than this value, the launch will fail.
FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT- On devices where the L1 cache and shared memory use the same hardware resources, this sets the shared memory carveout preference, in percent of the total shared memory. Refer toDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR.This is only a hint, and the driver can choose a different ratio if required to execute the function.
- See Also:
-
CU_FUNC_ATTRIBUTE_SHARED_SIZE_BYTES
public static final int CU_FUNC_ATTRIBUTE_SHARED_SIZE_BYTESFunction properties. (CUfunction_attribute)Enum values:
FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK- The maximum number of threads per block, beyond which a launch of the function would fail. This number depends on both the function and the device on which the function is currently loaded.FUNC_ATTRIBUTE_SHARED_SIZE_BYTES- The size in bytes of statically-allocated shared memory required by this function. This does not include dynamically-allocated shared memory requested by the user at runtime.FUNC_ATTRIBUTE_CONST_SIZE_BYTES- The size in bytes of user-allocated constant memory required by this function.FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES- The size in bytes of local memory used by each thread of this function.FUNC_ATTRIBUTE_NUM_REGS- The number of registers used by each thread of this function.FUNC_ATTRIBUTE_PTX_VERSION- The PTX virtual architecture version for which the function was compiled.This value is the major PTX
version * 10 + the minor PTX version, so a PTX version 1.3 function would return the value 13. Note that this may return the undefined value of 0 for cubins compiled prior to CUDA 3.0.FUNC_ATTRIBUTE_BINARY_VERSION- The binary architecture version for which the function was compiled.This value is the
major binary version * 10 + the minor binary version, so a binary version 1.3 function would return the value 13. Note that this will return a value of 10 for legacy cubins that do not have a properly-encoded binary architecture version.FUNC_ATTRIBUTE_CACHE_MODE_CA- The attribute to indicate whether the function has been compiled with user specified option"-Xptxas --dlcm=ca"set.FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES- The maximum size in bytes of dynamically-allocated shared memory that can be used by this function.If the user-specified dynamic shared memory size is larger than this value, the launch will fail.
FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT- On devices where the L1 cache and shared memory use the same hardware resources, this sets the shared memory carveout preference, in percent of the total shared memory. Refer toDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR.This is only a hint, and the driver can choose a different ratio if required to execute the function.
- See Also:
-
CU_FUNC_ATTRIBUTE_CONST_SIZE_BYTES
public static final int CU_FUNC_ATTRIBUTE_CONST_SIZE_BYTESFunction properties. (CUfunction_attribute)Enum values:
FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK- The maximum number of threads per block, beyond which a launch of the function would fail. This number depends on both the function and the device on which the function is currently loaded.FUNC_ATTRIBUTE_SHARED_SIZE_BYTES- The size in bytes of statically-allocated shared memory required by this function. This does not include dynamically-allocated shared memory requested by the user at runtime.FUNC_ATTRIBUTE_CONST_SIZE_BYTES- The size in bytes of user-allocated constant memory required by this function.FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES- The size in bytes of local memory used by each thread of this function.FUNC_ATTRIBUTE_NUM_REGS- The number of registers used by each thread of this function.FUNC_ATTRIBUTE_PTX_VERSION- The PTX virtual architecture version for which the function was compiled.This value is the major PTX
version * 10 + the minor PTX version, so a PTX version 1.3 function would return the value 13. Note that this may return the undefined value of 0 for cubins compiled prior to CUDA 3.0.FUNC_ATTRIBUTE_BINARY_VERSION- The binary architecture version for which the function was compiled.This value is the
major binary version * 10 + the minor binary version, so a binary version 1.3 function would return the value 13. Note that this will return a value of 10 for legacy cubins that do not have a properly-encoded binary architecture version.FUNC_ATTRIBUTE_CACHE_MODE_CA- The attribute to indicate whether the function has been compiled with user specified option"-Xptxas --dlcm=ca"set.FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES- The maximum size in bytes of dynamically-allocated shared memory that can be used by this function.If the user-specified dynamic shared memory size is larger than this value, the launch will fail.
FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT- On devices where the L1 cache and shared memory use the same hardware resources, this sets the shared memory carveout preference, in percent of the total shared memory. Refer toDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR.This is only a hint, and the driver can choose a different ratio if required to execute the function.
- See Also:
-
CU_FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES
public static final int CU_FUNC_ATTRIBUTE_LOCAL_SIZE_BYTESFunction properties. (CUfunction_attribute)Enum values:
FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK- The maximum number of threads per block, beyond which a launch of the function would fail. This number depends on both the function and the device on which the function is currently loaded.FUNC_ATTRIBUTE_SHARED_SIZE_BYTES- The size in bytes of statically-allocated shared memory required by this function. This does not include dynamically-allocated shared memory requested by the user at runtime.FUNC_ATTRIBUTE_CONST_SIZE_BYTES- The size in bytes of user-allocated constant memory required by this function.FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES- The size in bytes of local memory used by each thread of this function.FUNC_ATTRIBUTE_NUM_REGS- The number of registers used by each thread of this function.FUNC_ATTRIBUTE_PTX_VERSION- The PTX virtual architecture version for which the function was compiled.This value is the major PTX
version * 10 + the minor PTX version, so a PTX version 1.3 function would return the value 13. Note that this may return the undefined value of 0 for cubins compiled prior to CUDA 3.0.FUNC_ATTRIBUTE_BINARY_VERSION- The binary architecture version for which the function was compiled.This value is the
major binary version * 10 + the minor binary version, so a binary version 1.3 function would return the value 13. Note that this will return a value of 10 for legacy cubins that do not have a properly-encoded binary architecture version.FUNC_ATTRIBUTE_CACHE_MODE_CA- The attribute to indicate whether the function has been compiled with user specified option"-Xptxas --dlcm=ca"set.FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES- The maximum size in bytes of dynamically-allocated shared memory that can be used by this function.If the user-specified dynamic shared memory size is larger than this value, the launch will fail.
FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT- On devices where the L1 cache and shared memory use the same hardware resources, this sets the shared memory carveout preference, in percent of the total shared memory. Refer toDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR.This is only a hint, and the driver can choose a different ratio if required to execute the function.
- See Also:
-
CU_FUNC_ATTRIBUTE_NUM_REGS
public static final int CU_FUNC_ATTRIBUTE_NUM_REGSFunction properties. (CUfunction_attribute)Enum values:
FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK- The maximum number of threads per block, beyond which a launch of the function would fail. This number depends on both the function and the device on which the function is currently loaded.FUNC_ATTRIBUTE_SHARED_SIZE_BYTES- The size in bytes of statically-allocated shared memory required by this function. This does not include dynamically-allocated shared memory requested by the user at runtime.FUNC_ATTRIBUTE_CONST_SIZE_BYTES- The size in bytes of user-allocated constant memory required by this function.FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES- The size in bytes of local memory used by each thread of this function.FUNC_ATTRIBUTE_NUM_REGS- The number of registers used by each thread of this function.FUNC_ATTRIBUTE_PTX_VERSION- The PTX virtual architecture version for which the function was compiled.This value is the major PTX
version * 10 + the minor PTX version, so a PTX version 1.3 function would return the value 13. Note that this may return the undefined value of 0 for cubins compiled prior to CUDA 3.0.FUNC_ATTRIBUTE_BINARY_VERSION- The binary architecture version for which the function was compiled.This value is the
major binary version * 10 + the minor binary version, so a binary version 1.3 function would return the value 13. Note that this will return a value of 10 for legacy cubins that do not have a properly-encoded binary architecture version.FUNC_ATTRIBUTE_CACHE_MODE_CA- The attribute to indicate whether the function has been compiled with user specified option"-Xptxas --dlcm=ca"set.FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES- The maximum size in bytes of dynamically-allocated shared memory that can be used by this function.If the user-specified dynamic shared memory size is larger than this value, the launch will fail.
FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT- On devices where the L1 cache and shared memory use the same hardware resources, this sets the shared memory carveout preference, in percent of the total shared memory. Refer toDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR.This is only a hint, and the driver can choose a different ratio if required to execute the function.
- See Also:
-
CU_FUNC_ATTRIBUTE_PTX_VERSION
public static final int CU_FUNC_ATTRIBUTE_PTX_VERSIONFunction properties. (CUfunction_attribute)Enum values:
FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK- The maximum number of threads per block, beyond which a launch of the function would fail. This number depends on both the function and the device on which the function is currently loaded.FUNC_ATTRIBUTE_SHARED_SIZE_BYTES- The size in bytes of statically-allocated shared memory required by this function. This does not include dynamically-allocated shared memory requested by the user at runtime.FUNC_ATTRIBUTE_CONST_SIZE_BYTES- The size in bytes of user-allocated constant memory required by this function.FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES- The size in bytes of local memory used by each thread of this function.FUNC_ATTRIBUTE_NUM_REGS- The number of registers used by each thread of this function.FUNC_ATTRIBUTE_PTX_VERSION- The PTX virtual architecture version for which the function was compiled.This value is the major PTX
version * 10 + the minor PTX version, so a PTX version 1.3 function would return the value 13. Note that this may return the undefined value of 0 for cubins compiled prior to CUDA 3.0.FUNC_ATTRIBUTE_BINARY_VERSION- The binary architecture version for which the function was compiled.This value is the
major binary version * 10 + the minor binary version, so a binary version 1.3 function would return the value 13. Note that this will return a value of 10 for legacy cubins that do not have a properly-encoded binary architecture version.FUNC_ATTRIBUTE_CACHE_MODE_CA- The attribute to indicate whether the function has been compiled with user specified option"-Xptxas --dlcm=ca"set.FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES- The maximum size in bytes of dynamically-allocated shared memory that can be used by this function.If the user-specified dynamic shared memory size is larger than this value, the launch will fail.
FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT- On devices where the L1 cache and shared memory use the same hardware resources, this sets the shared memory carveout preference, in percent of the total shared memory. Refer toDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR.This is only a hint, and the driver can choose a different ratio if required to execute the function.
- See Also:
-
CU_FUNC_ATTRIBUTE_BINARY_VERSION
public static final int CU_FUNC_ATTRIBUTE_BINARY_VERSIONFunction properties. (CUfunction_attribute)Enum values:
FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK- The maximum number of threads per block, beyond which a launch of the function would fail. This number depends on both the function and the device on which the function is currently loaded.FUNC_ATTRIBUTE_SHARED_SIZE_BYTES- The size in bytes of statically-allocated shared memory required by this function. This does not include dynamically-allocated shared memory requested by the user at runtime.FUNC_ATTRIBUTE_CONST_SIZE_BYTES- The size in bytes of user-allocated constant memory required by this function.FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES- The size in bytes of local memory used by each thread of this function.FUNC_ATTRIBUTE_NUM_REGS- The number of registers used by each thread of this function.FUNC_ATTRIBUTE_PTX_VERSION- The PTX virtual architecture version for which the function was compiled.This value is the major PTX
version * 10 + the minor PTX version, so a PTX version 1.3 function would return the value 13. Note that this may return the undefined value of 0 for cubins compiled prior to CUDA 3.0.FUNC_ATTRIBUTE_BINARY_VERSION- The binary architecture version for which the function was compiled.This value is the
major binary version * 10 + the minor binary version, so a binary version 1.3 function would return the value 13. Note that this will return a value of 10 for legacy cubins that do not have a properly-encoded binary architecture version.FUNC_ATTRIBUTE_CACHE_MODE_CA- The attribute to indicate whether the function has been compiled with user specified option"-Xptxas --dlcm=ca"set.FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES- The maximum size in bytes of dynamically-allocated shared memory that can be used by this function.If the user-specified dynamic shared memory size is larger than this value, the launch will fail.
FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT- On devices where the L1 cache and shared memory use the same hardware resources, this sets the shared memory carveout preference, in percent of the total shared memory. Refer toDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR.This is only a hint, and the driver can choose a different ratio if required to execute the function.
- See Also:
-
CU_FUNC_ATTRIBUTE_CACHE_MODE_CA
public static final int CU_FUNC_ATTRIBUTE_CACHE_MODE_CAFunction properties. (CUfunction_attribute)Enum values:
FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK- The maximum number of threads per block, beyond which a launch of the function would fail. This number depends on both the function and the device on which the function is currently loaded.FUNC_ATTRIBUTE_SHARED_SIZE_BYTES- The size in bytes of statically-allocated shared memory required by this function. This does not include dynamically-allocated shared memory requested by the user at runtime.FUNC_ATTRIBUTE_CONST_SIZE_BYTES- The size in bytes of user-allocated constant memory required by this function.FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES- The size in bytes of local memory used by each thread of this function.FUNC_ATTRIBUTE_NUM_REGS- The number of registers used by each thread of this function.FUNC_ATTRIBUTE_PTX_VERSION- The PTX virtual architecture version for which the function was compiled.This value is the major PTX
version * 10 + the minor PTX version, so a PTX version 1.3 function would return the value 13. Note that this may return the undefined value of 0 for cubins compiled prior to CUDA 3.0.FUNC_ATTRIBUTE_BINARY_VERSION- The binary architecture version for which the function was compiled.This value is the
major binary version * 10 + the minor binary version, so a binary version 1.3 function would return the value 13. Note that this will return a value of 10 for legacy cubins that do not have a properly-encoded binary architecture version.FUNC_ATTRIBUTE_CACHE_MODE_CA- The attribute to indicate whether the function has been compiled with user specified option"-Xptxas --dlcm=ca"set.FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES- The maximum size in bytes of dynamically-allocated shared memory that can be used by this function.If the user-specified dynamic shared memory size is larger than this value, the launch will fail.
FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT- On devices where the L1 cache and shared memory use the same hardware resources, this sets the shared memory carveout preference, in percent of the total shared memory. Refer toDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR.This is only a hint, and the driver can choose a different ratio if required to execute the function.
- See Also:
-
CU_FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES
public static final int CU_FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTESFunction properties. (CUfunction_attribute)Enum values:
FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK- The maximum number of threads per block, beyond which a launch of the function would fail. This number depends on both the function and the device on which the function is currently loaded.FUNC_ATTRIBUTE_SHARED_SIZE_BYTES- The size in bytes of statically-allocated shared memory required by this function. This does not include dynamically-allocated shared memory requested by the user at runtime.FUNC_ATTRIBUTE_CONST_SIZE_BYTES- The size in bytes of user-allocated constant memory required by this function.FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES- The size in bytes of local memory used by each thread of this function.FUNC_ATTRIBUTE_NUM_REGS- The number of registers used by each thread of this function.FUNC_ATTRIBUTE_PTX_VERSION- The PTX virtual architecture version for which the function was compiled.This value is the major PTX
version * 10 + the minor PTX version, so a PTX version 1.3 function would return the value 13. Note that this may return the undefined value of 0 for cubins compiled prior to CUDA 3.0.FUNC_ATTRIBUTE_BINARY_VERSION- The binary architecture version for which the function was compiled.This value is the
major binary version * 10 + the minor binary version, so a binary version 1.3 function would return the value 13. Note that this will return a value of 10 for legacy cubins that do not have a properly-encoded binary architecture version.FUNC_ATTRIBUTE_CACHE_MODE_CA- The attribute to indicate whether the function has been compiled with user specified option"-Xptxas --dlcm=ca"set.FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES- The maximum size in bytes of dynamically-allocated shared memory that can be used by this function.If the user-specified dynamic shared memory size is larger than this value, the launch will fail.
FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT- On devices where the L1 cache and shared memory use the same hardware resources, this sets the shared memory carveout preference, in percent of the total shared memory. Refer toDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR.This is only a hint, and the driver can choose a different ratio if required to execute the function.
- See Also:
-
CU_FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT
public static final int CU_FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUTFunction properties. (CUfunction_attribute)Enum values:
FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK- The maximum number of threads per block, beyond which a launch of the function would fail. This number depends on both the function and the device on which the function is currently loaded.FUNC_ATTRIBUTE_SHARED_SIZE_BYTES- The size in bytes of statically-allocated shared memory required by this function. This does not include dynamically-allocated shared memory requested by the user at runtime.FUNC_ATTRIBUTE_CONST_SIZE_BYTES- The size in bytes of user-allocated constant memory required by this function.FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES- The size in bytes of local memory used by each thread of this function.FUNC_ATTRIBUTE_NUM_REGS- The number of registers used by each thread of this function.FUNC_ATTRIBUTE_PTX_VERSION- The PTX virtual architecture version for which the function was compiled.This value is the major PTX
version * 10 + the minor PTX version, so a PTX version 1.3 function would return the value 13. Note that this may return the undefined value of 0 for cubins compiled prior to CUDA 3.0.FUNC_ATTRIBUTE_BINARY_VERSION- The binary architecture version for which the function was compiled.This value is the
major binary version * 10 + the minor binary version, so a binary version 1.3 function would return the value 13. Note that this will return a value of 10 for legacy cubins that do not have a properly-encoded binary architecture version.FUNC_ATTRIBUTE_CACHE_MODE_CA- The attribute to indicate whether the function has been compiled with user specified option"-Xptxas --dlcm=ca"set.FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES- The maximum size in bytes of dynamically-allocated shared memory that can be used by this function.If the user-specified dynamic shared memory size is larger than this value, the launch will fail.
FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT- On devices where the L1 cache and shared memory use the same hardware resources, this sets the shared memory carveout preference, in percent of the total shared memory. Refer toDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR.This is only a hint, and the driver can choose a different ratio if required to execute the function.
- See Also:
-
CU_FUNC_CACHE_PREFER_NONE
public static final int CU_FUNC_CACHE_PREFER_NONEFunction cache configurations. (CUfunc_cache)Enum values:
FUNC_CACHE_PREFER_NONE- no preference for shared memory or L1 (default)FUNC_CACHE_PREFER_SHARED- prefer larger shared memory and smaller L1 cacheFUNC_CACHE_PREFER_L1- prefer larger L1 cache and smaller shared memoryFUNC_CACHE_PREFER_EQUAL- prefer equal sized L1 cache and shared memory
- See Also:
-
CU_FUNC_CACHE_PREFER_SHARED
public static final int CU_FUNC_CACHE_PREFER_SHAREDFunction cache configurations. (CUfunc_cache)Enum values:
FUNC_CACHE_PREFER_NONE- no preference for shared memory or L1 (default)FUNC_CACHE_PREFER_SHARED- prefer larger shared memory and smaller L1 cacheFUNC_CACHE_PREFER_L1- prefer larger L1 cache and smaller shared memoryFUNC_CACHE_PREFER_EQUAL- prefer equal sized L1 cache and shared memory
- See Also:
-
CU_FUNC_CACHE_PREFER_L1
public static final int CU_FUNC_CACHE_PREFER_L1Function cache configurations. (CUfunc_cache)Enum values:
FUNC_CACHE_PREFER_NONE- no preference for shared memory or L1 (default)FUNC_CACHE_PREFER_SHARED- prefer larger shared memory and smaller L1 cacheFUNC_CACHE_PREFER_L1- prefer larger L1 cache and smaller shared memoryFUNC_CACHE_PREFER_EQUAL- prefer equal sized L1 cache and shared memory
- See Also:
-
CU_FUNC_CACHE_PREFER_EQUAL
public static final int CU_FUNC_CACHE_PREFER_EQUALFunction cache configurations. (CUfunc_cache)Enum values:
FUNC_CACHE_PREFER_NONE- no preference for shared memory or L1 (default)FUNC_CACHE_PREFER_SHARED- prefer larger shared memory and smaller L1 cacheFUNC_CACHE_PREFER_L1- prefer larger L1 cache and smaller shared memoryFUNC_CACHE_PREFER_EQUAL- prefer equal sized L1 cache and shared memory
- See Also:
-
CU_SHARED_MEM_CONFIG_DEFAULT_BANK_SIZE
public static final int CU_SHARED_MEM_CONFIG_DEFAULT_BANK_SIZEShared memory configurations. (CUsharedconfig)Enum values:
SHARED_MEM_CONFIG_DEFAULT_BANK_SIZE- set default shared memory bank sizeSHARED_MEM_CONFIG_FOUR_BYTE_BANK_SIZE- set shared memory bank width to four bytesSHARED_MEM_CONFIG_EIGHT_BYTE_BANK_SIZE- set shared memory bank width to eight bytes
- See Also:
-
CU_SHARED_MEM_CONFIG_FOUR_BYTE_BANK_SIZE
public static final int CU_SHARED_MEM_CONFIG_FOUR_BYTE_BANK_SIZEShared memory configurations. (CUsharedconfig)Enum values:
SHARED_MEM_CONFIG_DEFAULT_BANK_SIZE- set default shared memory bank sizeSHARED_MEM_CONFIG_FOUR_BYTE_BANK_SIZE- set shared memory bank width to four bytesSHARED_MEM_CONFIG_EIGHT_BYTE_BANK_SIZE- set shared memory bank width to eight bytes
- See Also:
-
CU_SHARED_MEM_CONFIG_EIGHT_BYTE_BANK_SIZE
public static final int CU_SHARED_MEM_CONFIG_EIGHT_BYTE_BANK_SIZEShared memory configurations. (CUsharedconfig)Enum values:
SHARED_MEM_CONFIG_DEFAULT_BANK_SIZE- set default shared memory bank sizeSHARED_MEM_CONFIG_FOUR_BYTE_BANK_SIZE- set shared memory bank width to four bytesSHARED_MEM_CONFIG_EIGHT_BYTE_BANK_SIZE- set shared memory bank width to eight bytes
- See Also:
-
CU_SHAREDMEM_CARVEOUT_DEFAULT
public static final int CU_SHAREDMEM_CARVEOUT_DEFAULTShared memory carveout configurations. (CUshared_carveout)These may be passed to
FuncSetAttribute.Enum values:
SHAREDMEM_CARVEOUT_DEFAULT- no preference for shared memory or L1 (default)SHAREDMEM_CARVEOUT_MAX_SHARED- prefer maximum available shared memory, minimum L1 cacheSHAREDMEM_CARVEOUT_MAX_L1- prefer maximum available L1 cache, minimum shared memory
- See Also:
-
CU_SHAREDMEM_CARVEOUT_MAX_SHARED
public static final int CU_SHAREDMEM_CARVEOUT_MAX_SHAREDShared memory carveout configurations. (CUshared_carveout)These may be passed to
FuncSetAttribute.Enum values:
SHAREDMEM_CARVEOUT_DEFAULT- no preference for shared memory or L1 (default)SHAREDMEM_CARVEOUT_MAX_SHARED- prefer maximum available shared memory, minimum L1 cacheSHAREDMEM_CARVEOUT_MAX_L1- prefer maximum available L1 cache, minimum shared memory
- See Also:
-
CU_SHAREDMEM_CARVEOUT_MAX_L1
public static final int CU_SHAREDMEM_CARVEOUT_MAX_L1Shared memory carveout configurations. (CUshared_carveout)These may be passed to
FuncSetAttribute.Enum values:
SHAREDMEM_CARVEOUT_DEFAULT- no preference for shared memory or L1 (default)SHAREDMEM_CARVEOUT_MAX_SHARED- prefer maximum available shared memory, minimum L1 cacheSHAREDMEM_CARVEOUT_MAX_L1- prefer maximum available L1 cache, minimum shared memory
- See Also:
-
CU_MEMORYTYPE_HOST
public static final int CU_MEMORYTYPE_HOSTMemory types. (CUmemorytype)Enum values:
MEMORYTYPE_HOST- Host memoryMEMORYTYPE_DEVICE- Device memoryMEMORYTYPE_ARRAY- Array memoryMEMORYTYPE_UNIFIED- Unified device or host memory
- See Also:
-
CU_MEMORYTYPE_DEVICE
public static final int CU_MEMORYTYPE_DEVICEMemory types. (CUmemorytype)Enum values:
MEMORYTYPE_HOST- Host memoryMEMORYTYPE_DEVICE- Device memoryMEMORYTYPE_ARRAY- Array memoryMEMORYTYPE_UNIFIED- Unified device or host memory
- See Also:
-
CU_MEMORYTYPE_ARRAY
public static final int CU_MEMORYTYPE_ARRAYMemory types. (CUmemorytype)Enum values:
MEMORYTYPE_HOST- Host memoryMEMORYTYPE_DEVICE- Device memoryMEMORYTYPE_ARRAY- Array memoryMEMORYTYPE_UNIFIED- Unified device or host memory
- See Also:
-
CU_MEMORYTYPE_UNIFIED
public static final int CU_MEMORYTYPE_UNIFIEDMemory types. (CUmemorytype)Enum values:
MEMORYTYPE_HOST- Host memoryMEMORYTYPE_DEVICE- Device memoryMEMORYTYPE_ARRAY- Array memoryMEMORYTYPE_UNIFIED- Unified device or host memory
- See Also:
-
CU_COMPUTEMODE_DEFAULT
public static final int CU_COMPUTEMODE_DEFAULTCompute Modes. (CUcomputemode)Enum values:
COMPUTEMODE_DEFAULT- Default compute mode (Multiple contexts allowed per device)COMPUTEMODE_PROHIBITED- Compute-prohibited mode (No contexts can be created on this device at this time)COMPUTEMODE_EXCLUSIVE_PROCESS- Compute-exclusive-process mode (Only one context used by a single process can be present on this device at a time)
- See Also:
-
CU_COMPUTEMODE_PROHIBITED
public static final int CU_COMPUTEMODE_PROHIBITEDCompute Modes. (CUcomputemode)Enum values:
COMPUTEMODE_DEFAULT- Default compute mode (Multiple contexts allowed per device)COMPUTEMODE_PROHIBITED- Compute-prohibited mode (No contexts can be created on this device at this time)COMPUTEMODE_EXCLUSIVE_PROCESS- Compute-exclusive-process mode (Only one context used by a single process can be present on this device at a time)
- See Also:
-
CU_COMPUTEMODE_EXCLUSIVE_PROCESS
public static final int CU_COMPUTEMODE_EXCLUSIVE_PROCESSCompute Modes. (CUcomputemode)Enum values:
COMPUTEMODE_DEFAULT- Default compute mode (Multiple contexts allowed per device)COMPUTEMODE_PROHIBITED- Compute-prohibited mode (No contexts can be created on this device at this time)COMPUTEMODE_EXCLUSIVE_PROCESS- Compute-exclusive-process mode (Only one context used by a single process can be present on this device at a time)
- See Also:
-
CU_MEM_ADVISE_SET_READ_MOSTLY
public static final int CU_MEM_ADVISE_SET_READ_MOSTLYMemory advise values. (CUmem_advise)Enum values:
MEM_ADVISE_SET_READ_MOSTLY- Data will mostly be read and only occassionally be written toMEM_ADVISE_UNSET_READ_MOSTLY- Undo the effect ofMEM_ADVISE_SET_READ_MOSTLYMEM_ADVISE_SET_PREFERRED_LOCATION- Set the preferred location for the data as the specified deviceMEM_ADVISE_UNSET_PREFERRED_LOCATION- Clear the preferred location for the dataMEM_ADVISE_SET_ACCESSED_BY- Data will be accessed by the specified device, so prevent page faults as much as possibleMEM_ADVISE_UNSET_ACCESSED_BY- Let the Unified Memory subsystem decide on the page faulting policy for the specified device
- See Also:
-
CU_MEM_ADVISE_UNSET_READ_MOSTLY
public static final int CU_MEM_ADVISE_UNSET_READ_MOSTLYMemory advise values. (CUmem_advise)Enum values:
MEM_ADVISE_SET_READ_MOSTLY- Data will mostly be read and only occassionally be written toMEM_ADVISE_UNSET_READ_MOSTLY- Undo the effect ofMEM_ADVISE_SET_READ_MOSTLYMEM_ADVISE_SET_PREFERRED_LOCATION- Set the preferred location for the data as the specified deviceMEM_ADVISE_UNSET_PREFERRED_LOCATION- Clear the preferred location for the dataMEM_ADVISE_SET_ACCESSED_BY- Data will be accessed by the specified device, so prevent page faults as much as possibleMEM_ADVISE_UNSET_ACCESSED_BY- Let the Unified Memory subsystem decide on the page faulting policy for the specified device
- See Also:
-
CU_MEM_ADVISE_SET_PREFERRED_LOCATION
public static final int CU_MEM_ADVISE_SET_PREFERRED_LOCATIONMemory advise values. (CUmem_advise)Enum values:
MEM_ADVISE_SET_READ_MOSTLY- Data will mostly be read and only occassionally be written toMEM_ADVISE_UNSET_READ_MOSTLY- Undo the effect ofMEM_ADVISE_SET_READ_MOSTLYMEM_ADVISE_SET_PREFERRED_LOCATION- Set the preferred location for the data as the specified deviceMEM_ADVISE_UNSET_PREFERRED_LOCATION- Clear the preferred location for the dataMEM_ADVISE_SET_ACCESSED_BY- Data will be accessed by the specified device, so prevent page faults as much as possibleMEM_ADVISE_UNSET_ACCESSED_BY- Let the Unified Memory subsystem decide on the page faulting policy for the specified device
- See Also:
-
CU_MEM_ADVISE_UNSET_PREFERRED_LOCATION
public static final int CU_MEM_ADVISE_UNSET_PREFERRED_LOCATIONMemory advise values. (CUmem_advise)Enum values:
MEM_ADVISE_SET_READ_MOSTLY- Data will mostly be read and only occassionally be written toMEM_ADVISE_UNSET_READ_MOSTLY- Undo the effect ofMEM_ADVISE_SET_READ_MOSTLYMEM_ADVISE_SET_PREFERRED_LOCATION- Set the preferred location for the data as the specified deviceMEM_ADVISE_UNSET_PREFERRED_LOCATION- Clear the preferred location for the dataMEM_ADVISE_SET_ACCESSED_BY- Data will be accessed by the specified device, so prevent page faults as much as possibleMEM_ADVISE_UNSET_ACCESSED_BY- Let the Unified Memory subsystem decide on the page faulting policy for the specified device
- See Also:
-
CU_MEM_ADVISE_SET_ACCESSED_BY
public static final int CU_MEM_ADVISE_SET_ACCESSED_BYMemory advise values. (CUmem_advise)Enum values:
MEM_ADVISE_SET_READ_MOSTLY- Data will mostly be read and only occassionally be written toMEM_ADVISE_UNSET_READ_MOSTLY- Undo the effect ofMEM_ADVISE_SET_READ_MOSTLYMEM_ADVISE_SET_PREFERRED_LOCATION- Set the preferred location for the data as the specified deviceMEM_ADVISE_UNSET_PREFERRED_LOCATION- Clear the preferred location for the dataMEM_ADVISE_SET_ACCESSED_BY- Data will be accessed by the specified device, so prevent page faults as much as possibleMEM_ADVISE_UNSET_ACCESSED_BY- Let the Unified Memory subsystem decide on the page faulting policy for the specified device
- See Also:
-
CU_MEM_ADVISE_UNSET_ACCESSED_BY
public static final int CU_MEM_ADVISE_UNSET_ACCESSED_BYMemory advise values. (CUmem_advise)Enum values:
MEM_ADVISE_SET_READ_MOSTLY- Data will mostly be read and only occassionally be written toMEM_ADVISE_UNSET_READ_MOSTLY- Undo the effect ofMEM_ADVISE_SET_READ_MOSTLYMEM_ADVISE_SET_PREFERRED_LOCATION- Set the preferred location for the data as the specified deviceMEM_ADVISE_UNSET_PREFERRED_LOCATION- Clear the preferred location for the dataMEM_ADVISE_SET_ACCESSED_BY- Data will be accessed by the specified device, so prevent page faults as much as possibleMEM_ADVISE_UNSET_ACCESSED_BY- Let the Unified Memory subsystem decide on the page faulting policy for the specified device
- See Also:
-
CU_MEM_RANGE_ATTRIBUTE_READ_MOSTLY
public static final int CU_MEM_RANGE_ATTRIBUTE_READ_MOSTLY(CUmem_range_attribute)Enum values:
MEM_RANGE_ATTRIBUTE_READ_MOSTLY- Whether the range will mostly be read and only occassionally be written toMEM_RANGE_ATTRIBUTE_PREFERRED_LOCATION- The preferred location of the rangeMEM_RANGE_ATTRIBUTE_ACCESSED_BY- Memory range hasMEM_ADVISE_SET_ACCESSED_BYset for specified deviceMEM_RANGE_ATTRIBUTE_LAST_PREFETCH_LOCATION- The last location to which the range was prefetched
- See Also:
-
CU_MEM_RANGE_ATTRIBUTE_PREFERRED_LOCATION
public static final int CU_MEM_RANGE_ATTRIBUTE_PREFERRED_LOCATION(CUmem_range_attribute)Enum values:
MEM_RANGE_ATTRIBUTE_READ_MOSTLY- Whether the range will mostly be read and only occassionally be written toMEM_RANGE_ATTRIBUTE_PREFERRED_LOCATION- The preferred location of the rangeMEM_RANGE_ATTRIBUTE_ACCESSED_BY- Memory range hasMEM_ADVISE_SET_ACCESSED_BYset for specified deviceMEM_RANGE_ATTRIBUTE_LAST_PREFETCH_LOCATION- The last location to which the range was prefetched
- See Also:
-
CU_MEM_RANGE_ATTRIBUTE_ACCESSED_BY
public static final int CU_MEM_RANGE_ATTRIBUTE_ACCESSED_BY(CUmem_range_attribute)Enum values:
MEM_RANGE_ATTRIBUTE_READ_MOSTLY- Whether the range will mostly be read and only occassionally be written toMEM_RANGE_ATTRIBUTE_PREFERRED_LOCATION- The preferred location of the rangeMEM_RANGE_ATTRIBUTE_ACCESSED_BY- Memory range hasMEM_ADVISE_SET_ACCESSED_BYset for specified deviceMEM_RANGE_ATTRIBUTE_LAST_PREFETCH_LOCATION- The last location to which the range was prefetched
- See Also:
-
CU_MEM_RANGE_ATTRIBUTE_LAST_PREFETCH_LOCATION
public static final int CU_MEM_RANGE_ATTRIBUTE_LAST_PREFETCH_LOCATION(CUmem_range_attribute)Enum values:
MEM_RANGE_ATTRIBUTE_READ_MOSTLY- Whether the range will mostly be read and only occassionally be written toMEM_RANGE_ATTRIBUTE_PREFERRED_LOCATION- The preferred location of the rangeMEM_RANGE_ATTRIBUTE_ACCESSED_BY- Memory range hasMEM_ADVISE_SET_ACCESSED_BYset for specified deviceMEM_RANGE_ATTRIBUTE_LAST_PREFETCH_LOCATION- The last location to which the range was prefetched
- See Also:
-
CU_JIT_MAX_REGISTERS
public static final int CU_JIT_MAX_REGISTERSOnline compiler and linker options. (CUjit_option)Enum values:
JIT_MAX_REGISTERS- Max number of registers that a thread may use.Option type:
unsigned int. Applies to: compiler onlyJIT_THREADS_PER_BLOCK- IN: Specifies minimum number of threads per block to target compilation forOUT: Returns the number of threads the compiler actually targeted.
This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.
Cannot be combined with
JIT_TARGET. Option type:unsigned int. Applies to: compiler onlyJIT_WALL_TIME- Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.Option type:
float. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER- Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via optionJIT_INFO_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER- Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via optionJIT_ERROR_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_OPTIMIZATION_LEVEL- Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.Option type:
unsigned int. Applies to: compiler onlyJIT_TARGET_FROM_CUCONTEXT- No option value required. Determines the target based on the current attached context (default).Option type: No option value needed. Applies to: compiler and linker
JIT_TARGET- Target is chosen based on suppliedCUjit_target. Cannot be combined withJIT_THREADS_PER_BLOCK.Option type:
unsigned intfor enumerated typeCUjit_target. Applies to: compiler and linkerJIT_FALLBACK_STRATEGY- Specifies choice of fallback strategy if matching cubin is not found.Choice is based on supplied
CUjit_fallback. This option cannot be used withcuLink*APIs as the linker requires exact matches.Option type:
unsigned intfor enumerated typeCUjit_fallback. Applies to: compiler onlyJIT_GENERATE_DEBUG_INFO- Specifies whether to create debug information in output (-g) (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_LOG_VERBOSE- Generate verbose log messages (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_GENERATE_LINE_INFO- Generate line number information (-lineinfo) (0: false, default).Option type:
int. Applies to: compiler onlyJIT_CACHE_MODE- Specifies whether to enable caching explicitly (-dlcm). Choice is based on suppliedCUjit_cacheMode_enum.Option type:
unsigned intfor enumerated typeCUjit_cacheMode_enum. Applies to: compiler onlyJIT_NEW_SM3X_OPT- Used for internal purposes only, in this version of CUDA.JIT_FAST_COMPILE- Used for internal purposes only, in this version of CUDA.JIT_GLOBAL_SYMBOL_NAMES- Array of device symbol names that will be relocated to the corresponing host addresses stored inJIT_GLOBAL_SYMBOL_ADDRESSES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.Option type:
const char **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_ADDRESSES- Array of host addresses that will be used to relocate corresponding device symbols stored inJIT_GLOBAL_SYMBOL_NAMES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries.Option type:
void **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_COUNT- Number of entries inJIT_GLOBAL_SYMBOL_NAMESandJIT_GLOBAL_SYMBOL_ADDRESSESarrays.Option type:
unsigned int. Applies to: dynamic linker onlyJIT_LTO- Enable link-time optimization (-dlto) for device code (0: false, default)Option type:
int. Applies to: compiler and linkerJIT_FTZ- Control single-precision denormals (-ftz) support (0: false, default).- 1 : flushes denormal values to zero
- 0 : preserves denormal values
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_DIV- Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_SQRT- Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_FMA- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_NUM_OPTIONS- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTO
- See Also:
-
CU_JIT_THREADS_PER_BLOCK
public static final int CU_JIT_THREADS_PER_BLOCKOnline compiler and linker options. (CUjit_option)Enum values:
JIT_MAX_REGISTERS- Max number of registers that a thread may use.Option type:
unsigned int. Applies to: compiler onlyJIT_THREADS_PER_BLOCK- IN: Specifies minimum number of threads per block to target compilation forOUT: Returns the number of threads the compiler actually targeted.
This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.
Cannot be combined with
JIT_TARGET. Option type:unsigned int. Applies to: compiler onlyJIT_WALL_TIME- Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.Option type:
float. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER- Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via optionJIT_INFO_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER- Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via optionJIT_ERROR_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_OPTIMIZATION_LEVEL- Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.Option type:
unsigned int. Applies to: compiler onlyJIT_TARGET_FROM_CUCONTEXT- No option value required. Determines the target based on the current attached context (default).Option type: No option value needed. Applies to: compiler and linker
JIT_TARGET- Target is chosen based on suppliedCUjit_target. Cannot be combined withJIT_THREADS_PER_BLOCK.Option type:
unsigned intfor enumerated typeCUjit_target. Applies to: compiler and linkerJIT_FALLBACK_STRATEGY- Specifies choice of fallback strategy if matching cubin is not found.Choice is based on supplied
CUjit_fallback. This option cannot be used withcuLink*APIs as the linker requires exact matches.Option type:
unsigned intfor enumerated typeCUjit_fallback. Applies to: compiler onlyJIT_GENERATE_DEBUG_INFO- Specifies whether to create debug information in output (-g) (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_LOG_VERBOSE- Generate verbose log messages (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_GENERATE_LINE_INFO- Generate line number information (-lineinfo) (0: false, default).Option type:
int. Applies to: compiler onlyJIT_CACHE_MODE- Specifies whether to enable caching explicitly (-dlcm). Choice is based on suppliedCUjit_cacheMode_enum.Option type:
unsigned intfor enumerated typeCUjit_cacheMode_enum. Applies to: compiler onlyJIT_NEW_SM3X_OPT- Used for internal purposes only, in this version of CUDA.JIT_FAST_COMPILE- Used for internal purposes only, in this version of CUDA.JIT_GLOBAL_SYMBOL_NAMES- Array of device symbol names that will be relocated to the corresponing host addresses stored inJIT_GLOBAL_SYMBOL_ADDRESSES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.Option type:
const char **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_ADDRESSES- Array of host addresses that will be used to relocate corresponding device symbols stored inJIT_GLOBAL_SYMBOL_NAMES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries.Option type:
void **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_COUNT- Number of entries inJIT_GLOBAL_SYMBOL_NAMESandJIT_GLOBAL_SYMBOL_ADDRESSESarrays.Option type:
unsigned int. Applies to: dynamic linker onlyJIT_LTO- Enable link-time optimization (-dlto) for device code (0: false, default)Option type:
int. Applies to: compiler and linkerJIT_FTZ- Control single-precision denormals (-ftz) support (0: false, default).- 1 : flushes denormal values to zero
- 0 : preserves denormal values
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_DIV- Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_SQRT- Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_FMA- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_NUM_OPTIONS- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTO
- See Also:
-
CU_JIT_WALL_TIME
public static final int CU_JIT_WALL_TIMEOnline compiler and linker options. (CUjit_option)Enum values:
JIT_MAX_REGISTERS- Max number of registers that a thread may use.Option type:
unsigned int. Applies to: compiler onlyJIT_THREADS_PER_BLOCK- IN: Specifies minimum number of threads per block to target compilation forOUT: Returns the number of threads the compiler actually targeted.
This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.
Cannot be combined with
JIT_TARGET. Option type:unsigned int. Applies to: compiler onlyJIT_WALL_TIME- Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.Option type:
float. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER- Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via optionJIT_INFO_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER- Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via optionJIT_ERROR_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_OPTIMIZATION_LEVEL- Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.Option type:
unsigned int. Applies to: compiler onlyJIT_TARGET_FROM_CUCONTEXT- No option value required. Determines the target based on the current attached context (default).Option type: No option value needed. Applies to: compiler and linker
JIT_TARGET- Target is chosen based on suppliedCUjit_target. Cannot be combined withJIT_THREADS_PER_BLOCK.Option type:
unsigned intfor enumerated typeCUjit_target. Applies to: compiler and linkerJIT_FALLBACK_STRATEGY- Specifies choice of fallback strategy if matching cubin is not found.Choice is based on supplied
CUjit_fallback. This option cannot be used withcuLink*APIs as the linker requires exact matches.Option type:
unsigned intfor enumerated typeCUjit_fallback. Applies to: compiler onlyJIT_GENERATE_DEBUG_INFO- Specifies whether to create debug information in output (-g) (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_LOG_VERBOSE- Generate verbose log messages (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_GENERATE_LINE_INFO- Generate line number information (-lineinfo) (0: false, default).Option type:
int. Applies to: compiler onlyJIT_CACHE_MODE- Specifies whether to enable caching explicitly (-dlcm). Choice is based on suppliedCUjit_cacheMode_enum.Option type:
unsigned intfor enumerated typeCUjit_cacheMode_enum. Applies to: compiler onlyJIT_NEW_SM3X_OPT- Used for internal purposes only, in this version of CUDA.JIT_FAST_COMPILE- Used for internal purposes only, in this version of CUDA.JIT_GLOBAL_SYMBOL_NAMES- Array of device symbol names that will be relocated to the corresponing host addresses stored inJIT_GLOBAL_SYMBOL_ADDRESSES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.Option type:
const char **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_ADDRESSES- Array of host addresses that will be used to relocate corresponding device symbols stored inJIT_GLOBAL_SYMBOL_NAMES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries.Option type:
void **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_COUNT- Number of entries inJIT_GLOBAL_SYMBOL_NAMESandJIT_GLOBAL_SYMBOL_ADDRESSESarrays.Option type:
unsigned int. Applies to: dynamic linker onlyJIT_LTO- Enable link-time optimization (-dlto) for device code (0: false, default)Option type:
int. Applies to: compiler and linkerJIT_FTZ- Control single-precision denormals (-ftz) support (0: false, default).- 1 : flushes denormal values to zero
- 0 : preserves denormal values
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_DIV- Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_SQRT- Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_FMA- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_NUM_OPTIONS- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTO
- See Also:
-
CU_JIT_INFO_LOG_BUFFER
public static final int CU_JIT_INFO_LOG_BUFFEROnline compiler and linker options. (CUjit_option)Enum values:
JIT_MAX_REGISTERS- Max number of registers that a thread may use.Option type:
unsigned int. Applies to: compiler onlyJIT_THREADS_PER_BLOCK- IN: Specifies minimum number of threads per block to target compilation forOUT: Returns the number of threads the compiler actually targeted.
This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.
Cannot be combined with
JIT_TARGET. Option type:unsigned int. Applies to: compiler onlyJIT_WALL_TIME- Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.Option type:
float. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER- Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via optionJIT_INFO_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER- Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via optionJIT_ERROR_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_OPTIMIZATION_LEVEL- Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.Option type:
unsigned int. Applies to: compiler onlyJIT_TARGET_FROM_CUCONTEXT- No option value required. Determines the target based on the current attached context (default).Option type: No option value needed. Applies to: compiler and linker
JIT_TARGET- Target is chosen based on suppliedCUjit_target. Cannot be combined withJIT_THREADS_PER_BLOCK.Option type:
unsigned intfor enumerated typeCUjit_target. Applies to: compiler and linkerJIT_FALLBACK_STRATEGY- Specifies choice of fallback strategy if matching cubin is not found.Choice is based on supplied
CUjit_fallback. This option cannot be used withcuLink*APIs as the linker requires exact matches.Option type:
unsigned intfor enumerated typeCUjit_fallback. Applies to: compiler onlyJIT_GENERATE_DEBUG_INFO- Specifies whether to create debug information in output (-g) (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_LOG_VERBOSE- Generate verbose log messages (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_GENERATE_LINE_INFO- Generate line number information (-lineinfo) (0: false, default).Option type:
int. Applies to: compiler onlyJIT_CACHE_MODE- Specifies whether to enable caching explicitly (-dlcm). Choice is based on suppliedCUjit_cacheMode_enum.Option type:
unsigned intfor enumerated typeCUjit_cacheMode_enum. Applies to: compiler onlyJIT_NEW_SM3X_OPT- Used for internal purposes only, in this version of CUDA.JIT_FAST_COMPILE- Used for internal purposes only, in this version of CUDA.JIT_GLOBAL_SYMBOL_NAMES- Array of device symbol names that will be relocated to the corresponing host addresses stored inJIT_GLOBAL_SYMBOL_ADDRESSES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.Option type:
const char **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_ADDRESSES- Array of host addresses that will be used to relocate corresponding device symbols stored inJIT_GLOBAL_SYMBOL_NAMES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries.Option type:
void **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_COUNT- Number of entries inJIT_GLOBAL_SYMBOL_NAMESandJIT_GLOBAL_SYMBOL_ADDRESSESarrays.Option type:
unsigned int. Applies to: dynamic linker onlyJIT_LTO- Enable link-time optimization (-dlto) for device code (0: false, default)Option type:
int. Applies to: compiler and linkerJIT_FTZ- Control single-precision denormals (-ftz) support (0: false, default).- 1 : flushes denormal values to zero
- 0 : preserves denormal values
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_DIV- Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_SQRT- Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_FMA- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_NUM_OPTIONS- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTO
- See Also:
-
CU_JIT_INFO_LOG_BUFFER_SIZE_BYTES
public static final int CU_JIT_INFO_LOG_BUFFER_SIZE_BYTESOnline compiler and linker options. (CUjit_option)Enum values:
JIT_MAX_REGISTERS- Max number of registers that a thread may use.Option type:
unsigned int. Applies to: compiler onlyJIT_THREADS_PER_BLOCK- IN: Specifies minimum number of threads per block to target compilation forOUT: Returns the number of threads the compiler actually targeted.
This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.
Cannot be combined with
JIT_TARGET. Option type:unsigned int. Applies to: compiler onlyJIT_WALL_TIME- Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.Option type:
float. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER- Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via optionJIT_INFO_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER- Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via optionJIT_ERROR_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_OPTIMIZATION_LEVEL- Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.Option type:
unsigned int. Applies to: compiler onlyJIT_TARGET_FROM_CUCONTEXT- No option value required. Determines the target based on the current attached context (default).Option type: No option value needed. Applies to: compiler and linker
JIT_TARGET- Target is chosen based on suppliedCUjit_target. Cannot be combined withJIT_THREADS_PER_BLOCK.Option type:
unsigned intfor enumerated typeCUjit_target. Applies to: compiler and linkerJIT_FALLBACK_STRATEGY- Specifies choice of fallback strategy if matching cubin is not found.Choice is based on supplied
CUjit_fallback. This option cannot be used withcuLink*APIs as the linker requires exact matches.Option type:
unsigned intfor enumerated typeCUjit_fallback. Applies to: compiler onlyJIT_GENERATE_DEBUG_INFO- Specifies whether to create debug information in output (-g) (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_LOG_VERBOSE- Generate verbose log messages (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_GENERATE_LINE_INFO- Generate line number information (-lineinfo) (0: false, default).Option type:
int. Applies to: compiler onlyJIT_CACHE_MODE- Specifies whether to enable caching explicitly (-dlcm). Choice is based on suppliedCUjit_cacheMode_enum.Option type:
unsigned intfor enumerated typeCUjit_cacheMode_enum. Applies to: compiler onlyJIT_NEW_SM3X_OPT- Used for internal purposes only, in this version of CUDA.JIT_FAST_COMPILE- Used for internal purposes only, in this version of CUDA.JIT_GLOBAL_SYMBOL_NAMES- Array of device symbol names that will be relocated to the corresponing host addresses stored inJIT_GLOBAL_SYMBOL_ADDRESSES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.Option type:
const char **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_ADDRESSES- Array of host addresses that will be used to relocate corresponding device symbols stored inJIT_GLOBAL_SYMBOL_NAMES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries.Option type:
void **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_COUNT- Number of entries inJIT_GLOBAL_SYMBOL_NAMESandJIT_GLOBAL_SYMBOL_ADDRESSESarrays.Option type:
unsigned int. Applies to: dynamic linker onlyJIT_LTO- Enable link-time optimization (-dlto) for device code (0: false, default)Option type:
int. Applies to: compiler and linkerJIT_FTZ- Control single-precision denormals (-ftz) support (0: false, default).- 1 : flushes denormal values to zero
- 0 : preserves denormal values
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_DIV- Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_SQRT- Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_FMA- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_NUM_OPTIONS- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTO
- See Also:
-
CU_JIT_ERROR_LOG_BUFFER
public static final int CU_JIT_ERROR_LOG_BUFFEROnline compiler and linker options. (CUjit_option)Enum values:
JIT_MAX_REGISTERS- Max number of registers that a thread may use.Option type:
unsigned int. Applies to: compiler onlyJIT_THREADS_PER_BLOCK- IN: Specifies minimum number of threads per block to target compilation forOUT: Returns the number of threads the compiler actually targeted.
This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.
Cannot be combined with
JIT_TARGET. Option type:unsigned int. Applies to: compiler onlyJIT_WALL_TIME- Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.Option type:
float. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER- Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via optionJIT_INFO_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER- Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via optionJIT_ERROR_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_OPTIMIZATION_LEVEL- Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.Option type:
unsigned int. Applies to: compiler onlyJIT_TARGET_FROM_CUCONTEXT- No option value required. Determines the target based on the current attached context (default).Option type: No option value needed. Applies to: compiler and linker
JIT_TARGET- Target is chosen based on suppliedCUjit_target. Cannot be combined withJIT_THREADS_PER_BLOCK.Option type:
unsigned intfor enumerated typeCUjit_target. Applies to: compiler and linkerJIT_FALLBACK_STRATEGY- Specifies choice of fallback strategy if matching cubin is not found.Choice is based on supplied
CUjit_fallback. This option cannot be used withcuLink*APIs as the linker requires exact matches.Option type:
unsigned intfor enumerated typeCUjit_fallback. Applies to: compiler onlyJIT_GENERATE_DEBUG_INFO- Specifies whether to create debug information in output (-g) (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_LOG_VERBOSE- Generate verbose log messages (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_GENERATE_LINE_INFO- Generate line number information (-lineinfo) (0: false, default).Option type:
int. Applies to: compiler onlyJIT_CACHE_MODE- Specifies whether to enable caching explicitly (-dlcm). Choice is based on suppliedCUjit_cacheMode_enum.Option type:
unsigned intfor enumerated typeCUjit_cacheMode_enum. Applies to: compiler onlyJIT_NEW_SM3X_OPT- Used for internal purposes only, in this version of CUDA.JIT_FAST_COMPILE- Used for internal purposes only, in this version of CUDA.JIT_GLOBAL_SYMBOL_NAMES- Array of device symbol names that will be relocated to the corresponing host addresses stored inJIT_GLOBAL_SYMBOL_ADDRESSES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.Option type:
const char **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_ADDRESSES- Array of host addresses that will be used to relocate corresponding device symbols stored inJIT_GLOBAL_SYMBOL_NAMES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries.Option type:
void **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_COUNT- Number of entries inJIT_GLOBAL_SYMBOL_NAMESandJIT_GLOBAL_SYMBOL_ADDRESSESarrays.Option type:
unsigned int. Applies to: dynamic linker onlyJIT_LTO- Enable link-time optimization (-dlto) for device code (0: false, default)Option type:
int. Applies to: compiler and linkerJIT_FTZ- Control single-precision denormals (-ftz) support (0: false, default).- 1 : flushes denormal values to zero
- 0 : preserves denormal values
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_DIV- Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_SQRT- Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_FMA- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_NUM_OPTIONS- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTO
- See Also:
-
CU_JIT_ERROR_LOG_BUFFER_SIZE_BYTES
public static final int CU_JIT_ERROR_LOG_BUFFER_SIZE_BYTESOnline compiler and linker options. (CUjit_option)Enum values:
JIT_MAX_REGISTERS- Max number of registers that a thread may use.Option type:
unsigned int. Applies to: compiler onlyJIT_THREADS_PER_BLOCK- IN: Specifies minimum number of threads per block to target compilation forOUT: Returns the number of threads the compiler actually targeted.
This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.
Cannot be combined with
JIT_TARGET. Option type:unsigned int. Applies to: compiler onlyJIT_WALL_TIME- Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.Option type:
float. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER- Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via optionJIT_INFO_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER- Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via optionJIT_ERROR_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_OPTIMIZATION_LEVEL- Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.Option type:
unsigned int. Applies to: compiler onlyJIT_TARGET_FROM_CUCONTEXT- No option value required. Determines the target based on the current attached context (default).Option type: No option value needed. Applies to: compiler and linker
JIT_TARGET- Target is chosen based on suppliedCUjit_target. Cannot be combined withJIT_THREADS_PER_BLOCK.Option type:
unsigned intfor enumerated typeCUjit_target. Applies to: compiler and linkerJIT_FALLBACK_STRATEGY- Specifies choice of fallback strategy if matching cubin is not found.Choice is based on supplied
CUjit_fallback. This option cannot be used withcuLink*APIs as the linker requires exact matches.Option type:
unsigned intfor enumerated typeCUjit_fallback. Applies to: compiler onlyJIT_GENERATE_DEBUG_INFO- Specifies whether to create debug information in output (-g) (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_LOG_VERBOSE- Generate verbose log messages (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_GENERATE_LINE_INFO- Generate line number information (-lineinfo) (0: false, default).Option type:
int. Applies to: compiler onlyJIT_CACHE_MODE- Specifies whether to enable caching explicitly (-dlcm). Choice is based on suppliedCUjit_cacheMode_enum.Option type:
unsigned intfor enumerated typeCUjit_cacheMode_enum. Applies to: compiler onlyJIT_NEW_SM3X_OPT- Used for internal purposes only, in this version of CUDA.JIT_FAST_COMPILE- Used for internal purposes only, in this version of CUDA.JIT_GLOBAL_SYMBOL_NAMES- Array of device symbol names that will be relocated to the corresponing host addresses stored inJIT_GLOBAL_SYMBOL_ADDRESSES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.Option type:
const char **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_ADDRESSES- Array of host addresses that will be used to relocate corresponding device symbols stored inJIT_GLOBAL_SYMBOL_NAMES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries.Option type:
void **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_COUNT- Number of entries inJIT_GLOBAL_SYMBOL_NAMESandJIT_GLOBAL_SYMBOL_ADDRESSESarrays.Option type:
unsigned int. Applies to: dynamic linker onlyJIT_LTO- Enable link-time optimization (-dlto) for device code (0: false, default)Option type:
int. Applies to: compiler and linkerJIT_FTZ- Control single-precision denormals (-ftz) support (0: false, default).- 1 : flushes denormal values to zero
- 0 : preserves denormal values
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_DIV- Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_SQRT- Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_FMA- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_NUM_OPTIONS- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTO
- See Also:
-
CU_JIT_OPTIMIZATION_LEVEL
public static final int CU_JIT_OPTIMIZATION_LEVELOnline compiler and linker options. (CUjit_option)Enum values:
JIT_MAX_REGISTERS- Max number of registers that a thread may use.Option type:
unsigned int. Applies to: compiler onlyJIT_THREADS_PER_BLOCK- IN: Specifies minimum number of threads per block to target compilation forOUT: Returns the number of threads the compiler actually targeted.
This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.
Cannot be combined with
JIT_TARGET. Option type:unsigned int. Applies to: compiler onlyJIT_WALL_TIME- Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.Option type:
float. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER- Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via optionJIT_INFO_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER- Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via optionJIT_ERROR_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_OPTIMIZATION_LEVEL- Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.Option type:
unsigned int. Applies to: compiler onlyJIT_TARGET_FROM_CUCONTEXT- No option value required. Determines the target based on the current attached context (default).Option type: No option value needed. Applies to: compiler and linker
JIT_TARGET- Target is chosen based on suppliedCUjit_target. Cannot be combined withJIT_THREADS_PER_BLOCK.Option type:
unsigned intfor enumerated typeCUjit_target. Applies to: compiler and linkerJIT_FALLBACK_STRATEGY- Specifies choice of fallback strategy if matching cubin is not found.Choice is based on supplied
CUjit_fallback. This option cannot be used withcuLink*APIs as the linker requires exact matches.Option type:
unsigned intfor enumerated typeCUjit_fallback. Applies to: compiler onlyJIT_GENERATE_DEBUG_INFO- Specifies whether to create debug information in output (-g) (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_LOG_VERBOSE- Generate verbose log messages (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_GENERATE_LINE_INFO- Generate line number information (-lineinfo) (0: false, default).Option type:
int. Applies to: compiler onlyJIT_CACHE_MODE- Specifies whether to enable caching explicitly (-dlcm). Choice is based on suppliedCUjit_cacheMode_enum.Option type:
unsigned intfor enumerated typeCUjit_cacheMode_enum. Applies to: compiler onlyJIT_NEW_SM3X_OPT- Used for internal purposes only, in this version of CUDA.JIT_FAST_COMPILE- Used for internal purposes only, in this version of CUDA.JIT_GLOBAL_SYMBOL_NAMES- Array of device symbol names that will be relocated to the corresponing host addresses stored inJIT_GLOBAL_SYMBOL_ADDRESSES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.Option type:
const char **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_ADDRESSES- Array of host addresses that will be used to relocate corresponding device symbols stored inJIT_GLOBAL_SYMBOL_NAMES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries.Option type:
void **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_COUNT- Number of entries inJIT_GLOBAL_SYMBOL_NAMESandJIT_GLOBAL_SYMBOL_ADDRESSESarrays.Option type:
unsigned int. Applies to: dynamic linker onlyJIT_LTO- Enable link-time optimization (-dlto) for device code (0: false, default)Option type:
int. Applies to: compiler and linkerJIT_FTZ- Control single-precision denormals (-ftz) support (0: false, default).- 1 : flushes denormal values to zero
- 0 : preserves denormal values
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_DIV- Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_SQRT- Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_FMA- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_NUM_OPTIONS- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTO
- See Also:
-
CU_JIT_TARGET_FROM_CUCONTEXT
public static final int CU_JIT_TARGET_FROM_CUCONTEXTOnline compiler and linker options. (CUjit_option)Enum values:
JIT_MAX_REGISTERS- Max number of registers that a thread may use.Option type:
unsigned int. Applies to: compiler onlyJIT_THREADS_PER_BLOCK- IN: Specifies minimum number of threads per block to target compilation forOUT: Returns the number of threads the compiler actually targeted.
This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.
Cannot be combined with
JIT_TARGET. Option type:unsigned int. Applies to: compiler onlyJIT_WALL_TIME- Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.Option type:
float. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER- Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via optionJIT_INFO_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER- Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via optionJIT_ERROR_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_OPTIMIZATION_LEVEL- Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.Option type:
unsigned int. Applies to: compiler onlyJIT_TARGET_FROM_CUCONTEXT- No option value required. Determines the target based on the current attached context (default).Option type: No option value needed. Applies to: compiler and linker
JIT_TARGET- Target is chosen based on suppliedCUjit_target. Cannot be combined withJIT_THREADS_PER_BLOCK.Option type:
unsigned intfor enumerated typeCUjit_target. Applies to: compiler and linkerJIT_FALLBACK_STRATEGY- Specifies choice of fallback strategy if matching cubin is not found.Choice is based on supplied
CUjit_fallback. This option cannot be used withcuLink*APIs as the linker requires exact matches.Option type:
unsigned intfor enumerated typeCUjit_fallback. Applies to: compiler onlyJIT_GENERATE_DEBUG_INFO- Specifies whether to create debug information in output (-g) (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_LOG_VERBOSE- Generate verbose log messages (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_GENERATE_LINE_INFO- Generate line number information (-lineinfo) (0: false, default).Option type:
int. Applies to: compiler onlyJIT_CACHE_MODE- Specifies whether to enable caching explicitly (-dlcm). Choice is based on suppliedCUjit_cacheMode_enum.Option type:
unsigned intfor enumerated typeCUjit_cacheMode_enum. Applies to: compiler onlyJIT_NEW_SM3X_OPT- Used for internal purposes only, in this version of CUDA.JIT_FAST_COMPILE- Used for internal purposes only, in this version of CUDA.JIT_GLOBAL_SYMBOL_NAMES- Array of device symbol names that will be relocated to the corresponing host addresses stored inJIT_GLOBAL_SYMBOL_ADDRESSES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.Option type:
const char **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_ADDRESSES- Array of host addresses that will be used to relocate corresponding device symbols stored inJIT_GLOBAL_SYMBOL_NAMES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries.Option type:
void **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_COUNT- Number of entries inJIT_GLOBAL_SYMBOL_NAMESandJIT_GLOBAL_SYMBOL_ADDRESSESarrays.Option type:
unsigned int. Applies to: dynamic linker onlyJIT_LTO- Enable link-time optimization (-dlto) for device code (0: false, default)Option type:
int. Applies to: compiler and linkerJIT_FTZ- Control single-precision denormals (-ftz) support (0: false, default).- 1 : flushes denormal values to zero
- 0 : preserves denormal values
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_DIV- Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_SQRT- Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_FMA- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_NUM_OPTIONS- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTO
- See Also:
-
CU_JIT_TARGET
public static final int CU_JIT_TARGETOnline compiler and linker options. (CUjit_option)Enum values:
JIT_MAX_REGISTERS- Max number of registers that a thread may use.Option type:
unsigned int. Applies to: compiler onlyJIT_THREADS_PER_BLOCK- IN: Specifies minimum number of threads per block to target compilation forOUT: Returns the number of threads the compiler actually targeted.
This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.
Cannot be combined with
JIT_TARGET. Option type:unsigned int. Applies to: compiler onlyJIT_WALL_TIME- Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.Option type:
float. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER- Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via optionJIT_INFO_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER- Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via optionJIT_ERROR_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_OPTIMIZATION_LEVEL- Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.Option type:
unsigned int. Applies to: compiler onlyJIT_TARGET_FROM_CUCONTEXT- No option value required. Determines the target based on the current attached context (default).Option type: No option value needed. Applies to: compiler and linker
JIT_TARGET- Target is chosen based on suppliedCUjit_target. Cannot be combined withJIT_THREADS_PER_BLOCK.Option type:
unsigned intfor enumerated typeCUjit_target. Applies to: compiler and linkerJIT_FALLBACK_STRATEGY- Specifies choice of fallback strategy if matching cubin is not found.Choice is based on supplied
CUjit_fallback. This option cannot be used withcuLink*APIs as the linker requires exact matches.Option type:
unsigned intfor enumerated typeCUjit_fallback. Applies to: compiler onlyJIT_GENERATE_DEBUG_INFO- Specifies whether to create debug information in output (-g) (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_LOG_VERBOSE- Generate verbose log messages (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_GENERATE_LINE_INFO- Generate line number information (-lineinfo) (0: false, default).Option type:
int. Applies to: compiler onlyJIT_CACHE_MODE- Specifies whether to enable caching explicitly (-dlcm). Choice is based on suppliedCUjit_cacheMode_enum.Option type:
unsigned intfor enumerated typeCUjit_cacheMode_enum. Applies to: compiler onlyJIT_NEW_SM3X_OPT- Used for internal purposes only, in this version of CUDA.JIT_FAST_COMPILE- Used for internal purposes only, in this version of CUDA.JIT_GLOBAL_SYMBOL_NAMES- Array of device symbol names that will be relocated to the corresponing host addresses stored inJIT_GLOBAL_SYMBOL_ADDRESSES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.Option type:
const char **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_ADDRESSES- Array of host addresses that will be used to relocate corresponding device symbols stored inJIT_GLOBAL_SYMBOL_NAMES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries.Option type:
void **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_COUNT- Number of entries inJIT_GLOBAL_SYMBOL_NAMESandJIT_GLOBAL_SYMBOL_ADDRESSESarrays.Option type:
unsigned int. Applies to: dynamic linker onlyJIT_LTO- Enable link-time optimization (-dlto) for device code (0: false, default)Option type:
int. Applies to: compiler and linkerJIT_FTZ- Control single-precision denormals (-ftz) support (0: false, default).- 1 : flushes denormal values to zero
- 0 : preserves denormal values
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_DIV- Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_SQRT- Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_FMA- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_NUM_OPTIONS- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTO
- See Also:
-
CU_JIT_FALLBACK_STRATEGY
public static final int CU_JIT_FALLBACK_STRATEGYOnline compiler and linker options. (CUjit_option)Enum values:
JIT_MAX_REGISTERS- Max number of registers that a thread may use.Option type:
unsigned int. Applies to: compiler onlyJIT_THREADS_PER_BLOCK- IN: Specifies minimum number of threads per block to target compilation forOUT: Returns the number of threads the compiler actually targeted.
This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.
Cannot be combined with
JIT_TARGET. Option type:unsigned int. Applies to: compiler onlyJIT_WALL_TIME- Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.Option type:
float. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER- Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via optionJIT_INFO_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER- Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via optionJIT_ERROR_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_OPTIMIZATION_LEVEL- Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.Option type:
unsigned int. Applies to: compiler onlyJIT_TARGET_FROM_CUCONTEXT- No option value required. Determines the target based on the current attached context (default).Option type: No option value needed. Applies to: compiler and linker
JIT_TARGET- Target is chosen based on suppliedCUjit_target. Cannot be combined withJIT_THREADS_PER_BLOCK.Option type:
unsigned intfor enumerated typeCUjit_target. Applies to: compiler and linkerJIT_FALLBACK_STRATEGY- Specifies choice of fallback strategy if matching cubin is not found.Choice is based on supplied
CUjit_fallback. This option cannot be used withcuLink*APIs as the linker requires exact matches.Option type:
unsigned intfor enumerated typeCUjit_fallback. Applies to: compiler onlyJIT_GENERATE_DEBUG_INFO- Specifies whether to create debug information in output (-g) (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_LOG_VERBOSE- Generate verbose log messages (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_GENERATE_LINE_INFO- Generate line number information (-lineinfo) (0: false, default).Option type:
int. Applies to: compiler onlyJIT_CACHE_MODE- Specifies whether to enable caching explicitly (-dlcm). Choice is based on suppliedCUjit_cacheMode_enum.Option type:
unsigned intfor enumerated typeCUjit_cacheMode_enum. Applies to: compiler onlyJIT_NEW_SM3X_OPT- Used for internal purposes only, in this version of CUDA.JIT_FAST_COMPILE- Used for internal purposes only, in this version of CUDA.JIT_GLOBAL_SYMBOL_NAMES- Array of device symbol names that will be relocated to the corresponing host addresses stored inJIT_GLOBAL_SYMBOL_ADDRESSES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.Option type:
const char **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_ADDRESSES- Array of host addresses that will be used to relocate corresponding device symbols stored inJIT_GLOBAL_SYMBOL_NAMES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries.Option type:
void **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_COUNT- Number of entries inJIT_GLOBAL_SYMBOL_NAMESandJIT_GLOBAL_SYMBOL_ADDRESSESarrays.Option type:
unsigned int. Applies to: dynamic linker onlyJIT_LTO- Enable link-time optimization (-dlto) for device code (0: false, default)Option type:
int. Applies to: compiler and linkerJIT_FTZ- Control single-precision denormals (-ftz) support (0: false, default).- 1 : flushes denormal values to zero
- 0 : preserves denormal values
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_DIV- Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_SQRT- Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_FMA- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_NUM_OPTIONS- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTO
- See Also:
-
CU_JIT_GENERATE_DEBUG_INFO
public static final int CU_JIT_GENERATE_DEBUG_INFOOnline compiler and linker options. (CUjit_option)Enum values:
JIT_MAX_REGISTERS- Max number of registers that a thread may use.Option type:
unsigned int. Applies to: compiler onlyJIT_THREADS_PER_BLOCK- IN: Specifies minimum number of threads per block to target compilation forOUT: Returns the number of threads the compiler actually targeted.
This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.
Cannot be combined with
JIT_TARGET. Option type:unsigned int. Applies to: compiler onlyJIT_WALL_TIME- Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.Option type:
float. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER- Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via optionJIT_INFO_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER- Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via optionJIT_ERROR_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_OPTIMIZATION_LEVEL- Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.Option type:
unsigned int. Applies to: compiler onlyJIT_TARGET_FROM_CUCONTEXT- No option value required. Determines the target based on the current attached context (default).Option type: No option value needed. Applies to: compiler and linker
JIT_TARGET- Target is chosen based on suppliedCUjit_target. Cannot be combined withJIT_THREADS_PER_BLOCK.Option type:
unsigned intfor enumerated typeCUjit_target. Applies to: compiler and linkerJIT_FALLBACK_STRATEGY- Specifies choice of fallback strategy if matching cubin is not found.Choice is based on supplied
CUjit_fallback. This option cannot be used withcuLink*APIs as the linker requires exact matches.Option type:
unsigned intfor enumerated typeCUjit_fallback. Applies to: compiler onlyJIT_GENERATE_DEBUG_INFO- Specifies whether to create debug information in output (-g) (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_LOG_VERBOSE- Generate verbose log messages (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_GENERATE_LINE_INFO- Generate line number information (-lineinfo) (0: false, default).Option type:
int. Applies to: compiler onlyJIT_CACHE_MODE- Specifies whether to enable caching explicitly (-dlcm). Choice is based on suppliedCUjit_cacheMode_enum.Option type:
unsigned intfor enumerated typeCUjit_cacheMode_enum. Applies to: compiler onlyJIT_NEW_SM3X_OPT- Used for internal purposes only, in this version of CUDA.JIT_FAST_COMPILE- Used for internal purposes only, in this version of CUDA.JIT_GLOBAL_SYMBOL_NAMES- Array of device symbol names that will be relocated to the corresponing host addresses stored inJIT_GLOBAL_SYMBOL_ADDRESSES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.Option type:
const char **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_ADDRESSES- Array of host addresses that will be used to relocate corresponding device symbols stored inJIT_GLOBAL_SYMBOL_NAMES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries.Option type:
void **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_COUNT- Number of entries inJIT_GLOBAL_SYMBOL_NAMESandJIT_GLOBAL_SYMBOL_ADDRESSESarrays.Option type:
unsigned int. Applies to: dynamic linker onlyJIT_LTO- Enable link-time optimization (-dlto) for device code (0: false, default)Option type:
int. Applies to: compiler and linkerJIT_FTZ- Control single-precision denormals (-ftz) support (0: false, default).- 1 : flushes denormal values to zero
- 0 : preserves denormal values
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_DIV- Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_SQRT- Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_FMA- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_NUM_OPTIONS- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTO
- See Also:
-
CU_JIT_LOG_VERBOSE
public static final int CU_JIT_LOG_VERBOSEOnline compiler and linker options. (CUjit_option)Enum values:
JIT_MAX_REGISTERS- Max number of registers that a thread may use.Option type:
unsigned int. Applies to: compiler onlyJIT_THREADS_PER_BLOCK- IN: Specifies minimum number of threads per block to target compilation forOUT: Returns the number of threads the compiler actually targeted.
This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.
Cannot be combined with
JIT_TARGET. Option type:unsigned int. Applies to: compiler onlyJIT_WALL_TIME- Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.Option type:
float. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER- Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via optionJIT_INFO_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER- Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via optionJIT_ERROR_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_OPTIMIZATION_LEVEL- Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.Option type:
unsigned int. Applies to: compiler onlyJIT_TARGET_FROM_CUCONTEXT- No option value required. Determines the target based on the current attached context (default).Option type: No option value needed. Applies to: compiler and linker
JIT_TARGET- Target is chosen based on suppliedCUjit_target. Cannot be combined withJIT_THREADS_PER_BLOCK.Option type:
unsigned intfor enumerated typeCUjit_target. Applies to: compiler and linkerJIT_FALLBACK_STRATEGY- Specifies choice of fallback strategy if matching cubin is not found.Choice is based on supplied
CUjit_fallback. This option cannot be used withcuLink*APIs as the linker requires exact matches.Option type:
unsigned intfor enumerated typeCUjit_fallback. Applies to: compiler onlyJIT_GENERATE_DEBUG_INFO- Specifies whether to create debug information in output (-g) (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_LOG_VERBOSE- Generate verbose log messages (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_GENERATE_LINE_INFO- Generate line number information (-lineinfo) (0: false, default).Option type:
int. Applies to: compiler onlyJIT_CACHE_MODE- Specifies whether to enable caching explicitly (-dlcm). Choice is based on suppliedCUjit_cacheMode_enum.Option type:
unsigned intfor enumerated typeCUjit_cacheMode_enum. Applies to: compiler onlyJIT_NEW_SM3X_OPT- Used for internal purposes only, in this version of CUDA.JIT_FAST_COMPILE- Used for internal purposes only, in this version of CUDA.JIT_GLOBAL_SYMBOL_NAMES- Array of device symbol names that will be relocated to the corresponing host addresses stored inJIT_GLOBAL_SYMBOL_ADDRESSES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.Option type:
const char **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_ADDRESSES- Array of host addresses that will be used to relocate corresponding device symbols stored inJIT_GLOBAL_SYMBOL_NAMES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries.Option type:
void **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_COUNT- Number of entries inJIT_GLOBAL_SYMBOL_NAMESandJIT_GLOBAL_SYMBOL_ADDRESSESarrays.Option type:
unsigned int. Applies to: dynamic linker onlyJIT_LTO- Enable link-time optimization (-dlto) for device code (0: false, default)Option type:
int. Applies to: compiler and linkerJIT_FTZ- Control single-precision denormals (-ftz) support (0: false, default).- 1 : flushes denormal values to zero
- 0 : preserves denormal values
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_DIV- Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_SQRT- Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_FMA- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_NUM_OPTIONS- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTO
- See Also:
-
CU_JIT_GENERATE_LINE_INFO
public static final int CU_JIT_GENERATE_LINE_INFOOnline compiler and linker options. (CUjit_option)Enum values:
JIT_MAX_REGISTERS- Max number of registers that a thread may use.Option type:
unsigned int. Applies to: compiler onlyJIT_THREADS_PER_BLOCK- IN: Specifies minimum number of threads per block to target compilation forOUT: Returns the number of threads the compiler actually targeted.
This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.
Cannot be combined with
JIT_TARGET. Option type:unsigned int. Applies to: compiler onlyJIT_WALL_TIME- Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.Option type:
float. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER- Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via optionJIT_INFO_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER- Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via optionJIT_ERROR_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_OPTIMIZATION_LEVEL- Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.Option type:
unsigned int. Applies to: compiler onlyJIT_TARGET_FROM_CUCONTEXT- No option value required. Determines the target based on the current attached context (default).Option type: No option value needed. Applies to: compiler and linker
JIT_TARGET- Target is chosen based on suppliedCUjit_target. Cannot be combined withJIT_THREADS_PER_BLOCK.Option type:
unsigned intfor enumerated typeCUjit_target. Applies to: compiler and linkerJIT_FALLBACK_STRATEGY- Specifies choice of fallback strategy if matching cubin is not found.Choice is based on supplied
CUjit_fallback. This option cannot be used withcuLink*APIs as the linker requires exact matches.Option type:
unsigned intfor enumerated typeCUjit_fallback. Applies to: compiler onlyJIT_GENERATE_DEBUG_INFO- Specifies whether to create debug information in output (-g) (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_LOG_VERBOSE- Generate verbose log messages (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_GENERATE_LINE_INFO- Generate line number information (-lineinfo) (0: false, default).Option type:
int. Applies to: compiler onlyJIT_CACHE_MODE- Specifies whether to enable caching explicitly (-dlcm). Choice is based on suppliedCUjit_cacheMode_enum.Option type:
unsigned intfor enumerated typeCUjit_cacheMode_enum. Applies to: compiler onlyJIT_NEW_SM3X_OPT- Used for internal purposes only, in this version of CUDA.JIT_FAST_COMPILE- Used for internal purposes only, in this version of CUDA.JIT_GLOBAL_SYMBOL_NAMES- Array of device symbol names that will be relocated to the corresponing host addresses stored inJIT_GLOBAL_SYMBOL_ADDRESSES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.Option type:
const char **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_ADDRESSES- Array of host addresses that will be used to relocate corresponding device symbols stored inJIT_GLOBAL_SYMBOL_NAMES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries.Option type:
void **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_COUNT- Number of entries inJIT_GLOBAL_SYMBOL_NAMESandJIT_GLOBAL_SYMBOL_ADDRESSESarrays.Option type:
unsigned int. Applies to: dynamic linker onlyJIT_LTO- Enable link-time optimization (-dlto) for device code (0: false, default)Option type:
int. Applies to: compiler and linkerJIT_FTZ- Control single-precision denormals (-ftz) support (0: false, default).- 1 : flushes denormal values to zero
- 0 : preserves denormal values
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_DIV- Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_SQRT- Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_FMA- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_NUM_OPTIONS- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTO
- See Also:
-
CU_JIT_CACHE_MODE
public static final int CU_JIT_CACHE_MODEOnline compiler and linker options. (CUjit_option)Enum values:
JIT_MAX_REGISTERS- Max number of registers that a thread may use.Option type:
unsigned int. Applies to: compiler onlyJIT_THREADS_PER_BLOCK- IN: Specifies minimum number of threads per block to target compilation forOUT: Returns the number of threads the compiler actually targeted.
This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.
Cannot be combined with
JIT_TARGET. Option type:unsigned int. Applies to: compiler onlyJIT_WALL_TIME- Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.Option type:
float. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER- Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via optionJIT_INFO_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER- Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via optionJIT_ERROR_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_OPTIMIZATION_LEVEL- Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.Option type:
unsigned int. Applies to: compiler onlyJIT_TARGET_FROM_CUCONTEXT- No option value required. Determines the target based on the current attached context (default).Option type: No option value needed. Applies to: compiler and linker
JIT_TARGET- Target is chosen based on suppliedCUjit_target. Cannot be combined withJIT_THREADS_PER_BLOCK.Option type:
unsigned intfor enumerated typeCUjit_target. Applies to: compiler and linkerJIT_FALLBACK_STRATEGY- Specifies choice of fallback strategy if matching cubin is not found.Choice is based on supplied
CUjit_fallback. This option cannot be used withcuLink*APIs as the linker requires exact matches.Option type:
unsigned intfor enumerated typeCUjit_fallback. Applies to: compiler onlyJIT_GENERATE_DEBUG_INFO- Specifies whether to create debug information in output (-g) (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_LOG_VERBOSE- Generate verbose log messages (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_GENERATE_LINE_INFO- Generate line number information (-lineinfo) (0: false, default).Option type:
int. Applies to: compiler onlyJIT_CACHE_MODE- Specifies whether to enable caching explicitly (-dlcm). Choice is based on suppliedCUjit_cacheMode_enum.Option type:
unsigned intfor enumerated typeCUjit_cacheMode_enum. Applies to: compiler onlyJIT_NEW_SM3X_OPT- Used for internal purposes only, in this version of CUDA.JIT_FAST_COMPILE- Used for internal purposes only, in this version of CUDA.JIT_GLOBAL_SYMBOL_NAMES- Array of device symbol names that will be relocated to the corresponing host addresses stored inJIT_GLOBAL_SYMBOL_ADDRESSES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.Option type:
const char **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_ADDRESSES- Array of host addresses that will be used to relocate corresponding device symbols stored inJIT_GLOBAL_SYMBOL_NAMES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries.Option type:
void **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_COUNT- Number of entries inJIT_GLOBAL_SYMBOL_NAMESandJIT_GLOBAL_SYMBOL_ADDRESSESarrays.Option type:
unsigned int. Applies to: dynamic linker onlyJIT_LTO- Enable link-time optimization (-dlto) for device code (0: false, default)Option type:
int. Applies to: compiler and linkerJIT_FTZ- Control single-precision denormals (-ftz) support (0: false, default).- 1 : flushes denormal values to zero
- 0 : preserves denormal values
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_DIV- Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_SQRT- Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_FMA- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_NUM_OPTIONS- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTO
- See Also:
-
CU_JIT_NEW_SM3X_OPT
public static final int CU_JIT_NEW_SM3X_OPTOnline compiler and linker options. (CUjit_option)Enum values:
JIT_MAX_REGISTERS- Max number of registers that a thread may use.Option type:
unsigned int. Applies to: compiler onlyJIT_THREADS_PER_BLOCK- IN: Specifies minimum number of threads per block to target compilation forOUT: Returns the number of threads the compiler actually targeted.
This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.
Cannot be combined with
JIT_TARGET. Option type:unsigned int. Applies to: compiler onlyJIT_WALL_TIME- Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.Option type:
float. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER- Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via optionJIT_INFO_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER- Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via optionJIT_ERROR_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_OPTIMIZATION_LEVEL- Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.Option type:
unsigned int. Applies to: compiler onlyJIT_TARGET_FROM_CUCONTEXT- No option value required. Determines the target based on the current attached context (default).Option type: No option value needed. Applies to: compiler and linker
JIT_TARGET- Target is chosen based on suppliedCUjit_target. Cannot be combined withJIT_THREADS_PER_BLOCK.Option type:
unsigned intfor enumerated typeCUjit_target. Applies to: compiler and linkerJIT_FALLBACK_STRATEGY- Specifies choice of fallback strategy if matching cubin is not found.Choice is based on supplied
CUjit_fallback. This option cannot be used withcuLink*APIs as the linker requires exact matches.Option type:
unsigned intfor enumerated typeCUjit_fallback. Applies to: compiler onlyJIT_GENERATE_DEBUG_INFO- Specifies whether to create debug information in output (-g) (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_LOG_VERBOSE- Generate verbose log messages (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_GENERATE_LINE_INFO- Generate line number information (-lineinfo) (0: false, default).Option type:
int. Applies to: compiler onlyJIT_CACHE_MODE- Specifies whether to enable caching explicitly (-dlcm). Choice is based on suppliedCUjit_cacheMode_enum.Option type:
unsigned intfor enumerated typeCUjit_cacheMode_enum. Applies to: compiler onlyJIT_NEW_SM3X_OPT- Used for internal purposes only, in this version of CUDA.JIT_FAST_COMPILE- Used for internal purposes only, in this version of CUDA.JIT_GLOBAL_SYMBOL_NAMES- Array of device symbol names that will be relocated to the corresponing host addresses stored inJIT_GLOBAL_SYMBOL_ADDRESSES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.Option type:
const char **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_ADDRESSES- Array of host addresses that will be used to relocate corresponding device symbols stored inJIT_GLOBAL_SYMBOL_NAMES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries.Option type:
void **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_COUNT- Number of entries inJIT_GLOBAL_SYMBOL_NAMESandJIT_GLOBAL_SYMBOL_ADDRESSESarrays.Option type:
unsigned int. Applies to: dynamic linker onlyJIT_LTO- Enable link-time optimization (-dlto) for device code (0: false, default)Option type:
int. Applies to: compiler and linkerJIT_FTZ- Control single-precision denormals (-ftz) support (0: false, default).- 1 : flushes denormal values to zero
- 0 : preserves denormal values
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_DIV- Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_SQRT- Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_FMA- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_NUM_OPTIONS- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTO
- See Also:
-
CU_JIT_FAST_COMPILE
public static final int CU_JIT_FAST_COMPILEOnline compiler and linker options. (CUjit_option)Enum values:
JIT_MAX_REGISTERS- Max number of registers that a thread may use.Option type:
unsigned int. Applies to: compiler onlyJIT_THREADS_PER_BLOCK- IN: Specifies minimum number of threads per block to target compilation forOUT: Returns the number of threads the compiler actually targeted.
This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.
Cannot be combined with
JIT_TARGET. Option type:unsigned int. Applies to: compiler onlyJIT_WALL_TIME- Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.Option type:
float. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER- Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via optionJIT_INFO_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER- Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via optionJIT_ERROR_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_OPTIMIZATION_LEVEL- Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.Option type:
unsigned int. Applies to: compiler onlyJIT_TARGET_FROM_CUCONTEXT- No option value required. Determines the target based on the current attached context (default).Option type: No option value needed. Applies to: compiler and linker
JIT_TARGET- Target is chosen based on suppliedCUjit_target. Cannot be combined withJIT_THREADS_PER_BLOCK.Option type:
unsigned intfor enumerated typeCUjit_target. Applies to: compiler and linkerJIT_FALLBACK_STRATEGY- Specifies choice of fallback strategy if matching cubin is not found.Choice is based on supplied
CUjit_fallback. This option cannot be used withcuLink*APIs as the linker requires exact matches.Option type:
unsigned intfor enumerated typeCUjit_fallback. Applies to: compiler onlyJIT_GENERATE_DEBUG_INFO- Specifies whether to create debug information in output (-g) (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_LOG_VERBOSE- Generate verbose log messages (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_GENERATE_LINE_INFO- Generate line number information (-lineinfo) (0: false, default).Option type:
int. Applies to: compiler onlyJIT_CACHE_MODE- Specifies whether to enable caching explicitly (-dlcm). Choice is based on suppliedCUjit_cacheMode_enum.Option type:
unsigned intfor enumerated typeCUjit_cacheMode_enum. Applies to: compiler onlyJIT_NEW_SM3X_OPT- Used for internal purposes only, in this version of CUDA.JIT_FAST_COMPILE- Used for internal purposes only, in this version of CUDA.JIT_GLOBAL_SYMBOL_NAMES- Array of device symbol names that will be relocated to the corresponing host addresses stored inJIT_GLOBAL_SYMBOL_ADDRESSES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.Option type:
const char **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_ADDRESSES- Array of host addresses that will be used to relocate corresponding device symbols stored inJIT_GLOBAL_SYMBOL_NAMES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries.Option type:
void **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_COUNT- Number of entries inJIT_GLOBAL_SYMBOL_NAMESandJIT_GLOBAL_SYMBOL_ADDRESSESarrays.Option type:
unsigned int. Applies to: dynamic linker onlyJIT_LTO- Enable link-time optimization (-dlto) for device code (0: false, default)Option type:
int. Applies to: compiler and linkerJIT_FTZ- Control single-precision denormals (-ftz) support (0: false, default).- 1 : flushes denormal values to zero
- 0 : preserves denormal values
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_DIV- Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_SQRT- Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_FMA- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_NUM_OPTIONS- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTO
- See Also:
-
CU_JIT_GLOBAL_SYMBOL_NAMES
public static final int CU_JIT_GLOBAL_SYMBOL_NAMESOnline compiler and linker options. (CUjit_option)Enum values:
JIT_MAX_REGISTERS- Max number of registers that a thread may use.Option type:
unsigned int. Applies to: compiler onlyJIT_THREADS_PER_BLOCK- IN: Specifies minimum number of threads per block to target compilation forOUT: Returns the number of threads the compiler actually targeted.
This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.
Cannot be combined with
JIT_TARGET. Option type:unsigned int. Applies to: compiler onlyJIT_WALL_TIME- Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.Option type:
float. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER- Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via optionJIT_INFO_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER- Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via optionJIT_ERROR_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_OPTIMIZATION_LEVEL- Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.Option type:
unsigned int. Applies to: compiler onlyJIT_TARGET_FROM_CUCONTEXT- No option value required. Determines the target based on the current attached context (default).Option type: No option value needed. Applies to: compiler and linker
JIT_TARGET- Target is chosen based on suppliedCUjit_target. Cannot be combined withJIT_THREADS_PER_BLOCK.Option type:
unsigned intfor enumerated typeCUjit_target. Applies to: compiler and linkerJIT_FALLBACK_STRATEGY- Specifies choice of fallback strategy if matching cubin is not found.Choice is based on supplied
CUjit_fallback. This option cannot be used withcuLink*APIs as the linker requires exact matches.Option type:
unsigned intfor enumerated typeCUjit_fallback. Applies to: compiler onlyJIT_GENERATE_DEBUG_INFO- Specifies whether to create debug information in output (-g) (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_LOG_VERBOSE- Generate verbose log messages (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_GENERATE_LINE_INFO- Generate line number information (-lineinfo) (0: false, default).Option type:
int. Applies to: compiler onlyJIT_CACHE_MODE- Specifies whether to enable caching explicitly (-dlcm). Choice is based on suppliedCUjit_cacheMode_enum.Option type:
unsigned intfor enumerated typeCUjit_cacheMode_enum. Applies to: compiler onlyJIT_NEW_SM3X_OPT- Used for internal purposes only, in this version of CUDA.JIT_FAST_COMPILE- Used for internal purposes only, in this version of CUDA.JIT_GLOBAL_SYMBOL_NAMES- Array of device symbol names that will be relocated to the corresponing host addresses stored inJIT_GLOBAL_SYMBOL_ADDRESSES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.Option type:
const char **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_ADDRESSES- Array of host addresses that will be used to relocate corresponding device symbols stored inJIT_GLOBAL_SYMBOL_NAMES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries.Option type:
void **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_COUNT- Number of entries inJIT_GLOBAL_SYMBOL_NAMESandJIT_GLOBAL_SYMBOL_ADDRESSESarrays.Option type:
unsigned int. Applies to: dynamic linker onlyJIT_LTO- Enable link-time optimization (-dlto) for device code (0: false, default)Option type:
int. Applies to: compiler and linkerJIT_FTZ- Control single-precision denormals (-ftz) support (0: false, default).- 1 : flushes denormal values to zero
- 0 : preserves denormal values
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_DIV- Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_SQRT- Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_FMA- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_NUM_OPTIONS- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTO
- See Also:
-
CU_JIT_GLOBAL_SYMBOL_ADDRESSES
public static final int CU_JIT_GLOBAL_SYMBOL_ADDRESSESOnline compiler and linker options. (CUjit_option)Enum values:
JIT_MAX_REGISTERS- Max number of registers that a thread may use.Option type:
unsigned int. Applies to: compiler onlyJIT_THREADS_PER_BLOCK- IN: Specifies minimum number of threads per block to target compilation forOUT: Returns the number of threads the compiler actually targeted.
This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.
Cannot be combined with
JIT_TARGET. Option type:unsigned int. Applies to: compiler onlyJIT_WALL_TIME- Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.Option type:
float. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER- Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via optionJIT_INFO_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER- Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via optionJIT_ERROR_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_OPTIMIZATION_LEVEL- Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.Option type:
unsigned int. Applies to: compiler onlyJIT_TARGET_FROM_CUCONTEXT- No option value required. Determines the target based on the current attached context (default).Option type: No option value needed. Applies to: compiler and linker
JIT_TARGET- Target is chosen based on suppliedCUjit_target. Cannot be combined withJIT_THREADS_PER_BLOCK.Option type:
unsigned intfor enumerated typeCUjit_target. Applies to: compiler and linkerJIT_FALLBACK_STRATEGY- Specifies choice of fallback strategy if matching cubin is not found.Choice is based on supplied
CUjit_fallback. This option cannot be used withcuLink*APIs as the linker requires exact matches.Option type:
unsigned intfor enumerated typeCUjit_fallback. Applies to: compiler onlyJIT_GENERATE_DEBUG_INFO- Specifies whether to create debug information in output (-g) (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_LOG_VERBOSE- Generate verbose log messages (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_GENERATE_LINE_INFO- Generate line number information (-lineinfo) (0: false, default).Option type:
int. Applies to: compiler onlyJIT_CACHE_MODE- Specifies whether to enable caching explicitly (-dlcm). Choice is based on suppliedCUjit_cacheMode_enum.Option type:
unsigned intfor enumerated typeCUjit_cacheMode_enum. Applies to: compiler onlyJIT_NEW_SM3X_OPT- Used for internal purposes only, in this version of CUDA.JIT_FAST_COMPILE- Used for internal purposes only, in this version of CUDA.JIT_GLOBAL_SYMBOL_NAMES- Array of device symbol names that will be relocated to the corresponing host addresses stored inJIT_GLOBAL_SYMBOL_ADDRESSES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.Option type:
const char **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_ADDRESSES- Array of host addresses that will be used to relocate corresponding device symbols stored inJIT_GLOBAL_SYMBOL_NAMES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries.Option type:
void **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_COUNT- Number of entries inJIT_GLOBAL_SYMBOL_NAMESandJIT_GLOBAL_SYMBOL_ADDRESSESarrays.Option type:
unsigned int. Applies to: dynamic linker onlyJIT_LTO- Enable link-time optimization (-dlto) for device code (0: false, default)Option type:
int. Applies to: compiler and linkerJIT_FTZ- Control single-precision denormals (-ftz) support (0: false, default).- 1 : flushes denormal values to zero
- 0 : preserves denormal values
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_DIV- Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_SQRT- Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_FMA- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_NUM_OPTIONS- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTO
- See Also:
-
CU_JIT_GLOBAL_SYMBOL_COUNT
public static final int CU_JIT_GLOBAL_SYMBOL_COUNTOnline compiler and linker options. (CUjit_option)Enum values:
JIT_MAX_REGISTERS- Max number of registers that a thread may use.Option type:
unsigned int. Applies to: compiler onlyJIT_THREADS_PER_BLOCK- IN: Specifies minimum number of threads per block to target compilation forOUT: Returns the number of threads the compiler actually targeted.
This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.
Cannot be combined with
JIT_TARGET. Option type:unsigned int. Applies to: compiler onlyJIT_WALL_TIME- Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.Option type:
float. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER- Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via optionJIT_INFO_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER- Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via optionJIT_ERROR_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_OPTIMIZATION_LEVEL- Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.Option type:
unsigned int. Applies to: compiler onlyJIT_TARGET_FROM_CUCONTEXT- No option value required. Determines the target based on the current attached context (default).Option type: No option value needed. Applies to: compiler and linker
JIT_TARGET- Target is chosen based on suppliedCUjit_target. Cannot be combined withJIT_THREADS_PER_BLOCK.Option type:
unsigned intfor enumerated typeCUjit_target. Applies to: compiler and linkerJIT_FALLBACK_STRATEGY- Specifies choice of fallback strategy if matching cubin is not found.Choice is based on supplied
CUjit_fallback. This option cannot be used withcuLink*APIs as the linker requires exact matches.Option type:
unsigned intfor enumerated typeCUjit_fallback. Applies to: compiler onlyJIT_GENERATE_DEBUG_INFO- Specifies whether to create debug information in output (-g) (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_LOG_VERBOSE- Generate verbose log messages (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_GENERATE_LINE_INFO- Generate line number information (-lineinfo) (0: false, default).Option type:
int. Applies to: compiler onlyJIT_CACHE_MODE- Specifies whether to enable caching explicitly (-dlcm). Choice is based on suppliedCUjit_cacheMode_enum.Option type:
unsigned intfor enumerated typeCUjit_cacheMode_enum. Applies to: compiler onlyJIT_NEW_SM3X_OPT- Used for internal purposes only, in this version of CUDA.JIT_FAST_COMPILE- Used for internal purposes only, in this version of CUDA.JIT_GLOBAL_SYMBOL_NAMES- Array of device symbol names that will be relocated to the corresponing host addresses stored inJIT_GLOBAL_SYMBOL_ADDRESSES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.Option type:
const char **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_ADDRESSES- Array of host addresses that will be used to relocate corresponding device symbols stored inJIT_GLOBAL_SYMBOL_NAMES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries.Option type:
void **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_COUNT- Number of entries inJIT_GLOBAL_SYMBOL_NAMESandJIT_GLOBAL_SYMBOL_ADDRESSESarrays.Option type:
unsigned int. Applies to: dynamic linker onlyJIT_LTO- Enable link-time optimization (-dlto) for device code (0: false, default)Option type:
int. Applies to: compiler and linkerJIT_FTZ- Control single-precision denormals (-ftz) support (0: false, default).- 1 : flushes denormal values to zero
- 0 : preserves denormal values
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_DIV- Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_SQRT- Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_FMA- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_NUM_OPTIONS- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTO
- See Also:
-
CU_JIT_LTO
public static final int CU_JIT_LTOOnline compiler and linker options. (CUjit_option)Enum values:
JIT_MAX_REGISTERS- Max number of registers that a thread may use.Option type:
unsigned int. Applies to: compiler onlyJIT_THREADS_PER_BLOCK- IN: Specifies minimum number of threads per block to target compilation forOUT: Returns the number of threads the compiler actually targeted.
This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.
Cannot be combined with
JIT_TARGET. Option type:unsigned int. Applies to: compiler onlyJIT_WALL_TIME- Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.Option type:
float. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER- Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via optionJIT_INFO_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER- Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via optionJIT_ERROR_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_OPTIMIZATION_LEVEL- Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.Option type:
unsigned int. Applies to: compiler onlyJIT_TARGET_FROM_CUCONTEXT- No option value required. Determines the target based on the current attached context (default).Option type: No option value needed. Applies to: compiler and linker
JIT_TARGET- Target is chosen based on suppliedCUjit_target. Cannot be combined withJIT_THREADS_PER_BLOCK.Option type:
unsigned intfor enumerated typeCUjit_target. Applies to: compiler and linkerJIT_FALLBACK_STRATEGY- Specifies choice of fallback strategy if matching cubin is not found.Choice is based on supplied
CUjit_fallback. This option cannot be used withcuLink*APIs as the linker requires exact matches.Option type:
unsigned intfor enumerated typeCUjit_fallback. Applies to: compiler onlyJIT_GENERATE_DEBUG_INFO- Specifies whether to create debug information in output (-g) (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_LOG_VERBOSE- Generate verbose log messages (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_GENERATE_LINE_INFO- Generate line number information (-lineinfo) (0: false, default).Option type:
int. Applies to: compiler onlyJIT_CACHE_MODE- Specifies whether to enable caching explicitly (-dlcm). Choice is based on suppliedCUjit_cacheMode_enum.Option type:
unsigned intfor enumerated typeCUjit_cacheMode_enum. Applies to: compiler onlyJIT_NEW_SM3X_OPT- Used for internal purposes only, in this version of CUDA.JIT_FAST_COMPILE- Used for internal purposes only, in this version of CUDA.JIT_GLOBAL_SYMBOL_NAMES- Array of device symbol names that will be relocated to the corresponing host addresses stored inJIT_GLOBAL_SYMBOL_ADDRESSES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.Option type:
const char **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_ADDRESSES- Array of host addresses that will be used to relocate corresponding device symbols stored inJIT_GLOBAL_SYMBOL_NAMES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries.Option type:
void **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_COUNT- Number of entries inJIT_GLOBAL_SYMBOL_NAMESandJIT_GLOBAL_SYMBOL_ADDRESSESarrays.Option type:
unsigned int. Applies to: dynamic linker onlyJIT_LTO- Enable link-time optimization (-dlto) for device code (0: false, default)Option type:
int. Applies to: compiler and linkerJIT_FTZ- Control single-precision denormals (-ftz) support (0: false, default).- 1 : flushes denormal values to zero
- 0 : preserves denormal values
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_DIV- Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_SQRT- Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_FMA- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_NUM_OPTIONS- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTO
- See Also:
-
CU_JIT_FTZ
public static final int CU_JIT_FTZOnline compiler and linker options. (CUjit_option)Enum values:
JIT_MAX_REGISTERS- Max number of registers that a thread may use.Option type:
unsigned int. Applies to: compiler onlyJIT_THREADS_PER_BLOCK- IN: Specifies minimum number of threads per block to target compilation forOUT: Returns the number of threads the compiler actually targeted.
This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.
Cannot be combined with
JIT_TARGET. Option type:unsigned int. Applies to: compiler onlyJIT_WALL_TIME- Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.Option type:
float. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER- Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via optionJIT_INFO_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER- Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via optionJIT_ERROR_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_OPTIMIZATION_LEVEL- Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.Option type:
unsigned int. Applies to: compiler onlyJIT_TARGET_FROM_CUCONTEXT- No option value required. Determines the target based on the current attached context (default).Option type: No option value needed. Applies to: compiler and linker
JIT_TARGET- Target is chosen based on suppliedCUjit_target. Cannot be combined withJIT_THREADS_PER_BLOCK.Option type:
unsigned intfor enumerated typeCUjit_target. Applies to: compiler and linkerJIT_FALLBACK_STRATEGY- Specifies choice of fallback strategy if matching cubin is not found.Choice is based on supplied
CUjit_fallback. This option cannot be used withcuLink*APIs as the linker requires exact matches.Option type:
unsigned intfor enumerated typeCUjit_fallback. Applies to: compiler onlyJIT_GENERATE_DEBUG_INFO- Specifies whether to create debug information in output (-g) (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_LOG_VERBOSE- Generate verbose log messages (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_GENERATE_LINE_INFO- Generate line number information (-lineinfo) (0: false, default).Option type:
int. Applies to: compiler onlyJIT_CACHE_MODE- Specifies whether to enable caching explicitly (-dlcm). Choice is based on suppliedCUjit_cacheMode_enum.Option type:
unsigned intfor enumerated typeCUjit_cacheMode_enum. Applies to: compiler onlyJIT_NEW_SM3X_OPT- Used for internal purposes only, in this version of CUDA.JIT_FAST_COMPILE- Used for internal purposes only, in this version of CUDA.JIT_GLOBAL_SYMBOL_NAMES- Array of device symbol names that will be relocated to the corresponing host addresses stored inJIT_GLOBAL_SYMBOL_ADDRESSES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.Option type:
const char **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_ADDRESSES- Array of host addresses that will be used to relocate corresponding device symbols stored inJIT_GLOBAL_SYMBOL_NAMES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries.Option type:
void **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_COUNT- Number of entries inJIT_GLOBAL_SYMBOL_NAMESandJIT_GLOBAL_SYMBOL_ADDRESSESarrays.Option type:
unsigned int. Applies to: dynamic linker onlyJIT_LTO- Enable link-time optimization (-dlto) for device code (0: false, default)Option type:
int. Applies to: compiler and linkerJIT_FTZ- Control single-precision denormals (-ftz) support (0: false, default).- 1 : flushes denormal values to zero
- 0 : preserves denormal values
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_DIV- Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_SQRT- Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_FMA- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_NUM_OPTIONS- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTO
- See Also:
-
CU_JIT_PREC_DIV
public static final int CU_JIT_PREC_DIVOnline compiler and linker options. (CUjit_option)Enum values:
JIT_MAX_REGISTERS- Max number of registers that a thread may use.Option type:
unsigned int. Applies to: compiler onlyJIT_THREADS_PER_BLOCK- IN: Specifies minimum number of threads per block to target compilation forOUT: Returns the number of threads the compiler actually targeted.
This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.
Cannot be combined with
JIT_TARGET. Option type:unsigned int. Applies to: compiler onlyJIT_WALL_TIME- Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.Option type:
float. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER- Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via optionJIT_INFO_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER- Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via optionJIT_ERROR_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_OPTIMIZATION_LEVEL- Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.Option type:
unsigned int. Applies to: compiler onlyJIT_TARGET_FROM_CUCONTEXT- No option value required. Determines the target based on the current attached context (default).Option type: No option value needed. Applies to: compiler and linker
JIT_TARGET- Target is chosen based on suppliedCUjit_target. Cannot be combined withJIT_THREADS_PER_BLOCK.Option type:
unsigned intfor enumerated typeCUjit_target. Applies to: compiler and linkerJIT_FALLBACK_STRATEGY- Specifies choice of fallback strategy if matching cubin is not found.Choice is based on supplied
CUjit_fallback. This option cannot be used withcuLink*APIs as the linker requires exact matches.Option type:
unsigned intfor enumerated typeCUjit_fallback. Applies to: compiler onlyJIT_GENERATE_DEBUG_INFO- Specifies whether to create debug information in output (-g) (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_LOG_VERBOSE- Generate verbose log messages (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_GENERATE_LINE_INFO- Generate line number information (-lineinfo) (0: false, default).Option type:
int. Applies to: compiler onlyJIT_CACHE_MODE- Specifies whether to enable caching explicitly (-dlcm). Choice is based on suppliedCUjit_cacheMode_enum.Option type:
unsigned intfor enumerated typeCUjit_cacheMode_enum. Applies to: compiler onlyJIT_NEW_SM3X_OPT- Used for internal purposes only, in this version of CUDA.JIT_FAST_COMPILE- Used for internal purposes only, in this version of CUDA.JIT_GLOBAL_SYMBOL_NAMES- Array of device symbol names that will be relocated to the corresponing host addresses stored inJIT_GLOBAL_SYMBOL_ADDRESSES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.Option type:
const char **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_ADDRESSES- Array of host addresses that will be used to relocate corresponding device symbols stored inJIT_GLOBAL_SYMBOL_NAMES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries.Option type:
void **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_COUNT- Number of entries inJIT_GLOBAL_SYMBOL_NAMESandJIT_GLOBAL_SYMBOL_ADDRESSESarrays.Option type:
unsigned int. Applies to: dynamic linker onlyJIT_LTO- Enable link-time optimization (-dlto) for device code (0: false, default)Option type:
int. Applies to: compiler and linkerJIT_FTZ- Control single-precision denormals (-ftz) support (0: false, default).- 1 : flushes denormal values to zero
- 0 : preserves denormal values
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_DIV- Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_SQRT- Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_FMA- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_NUM_OPTIONS- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTO
- See Also:
-
CU_JIT_PREC_SQRT
public static final int CU_JIT_PREC_SQRTOnline compiler and linker options. (CUjit_option)Enum values:
JIT_MAX_REGISTERS- Max number of registers that a thread may use.Option type:
unsigned int. Applies to: compiler onlyJIT_THREADS_PER_BLOCK- IN: Specifies minimum number of threads per block to target compilation forOUT: Returns the number of threads the compiler actually targeted.
This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.
Cannot be combined with
JIT_TARGET. Option type:unsigned int. Applies to: compiler onlyJIT_WALL_TIME- Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.Option type:
float. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER- Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via optionJIT_INFO_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER- Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via optionJIT_ERROR_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_OPTIMIZATION_LEVEL- Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.Option type:
unsigned int. Applies to: compiler onlyJIT_TARGET_FROM_CUCONTEXT- No option value required. Determines the target based on the current attached context (default).Option type: No option value needed. Applies to: compiler and linker
JIT_TARGET- Target is chosen based on suppliedCUjit_target. Cannot be combined withJIT_THREADS_PER_BLOCK.Option type:
unsigned intfor enumerated typeCUjit_target. Applies to: compiler and linkerJIT_FALLBACK_STRATEGY- Specifies choice of fallback strategy if matching cubin is not found.Choice is based on supplied
CUjit_fallback. This option cannot be used withcuLink*APIs as the linker requires exact matches.Option type:
unsigned intfor enumerated typeCUjit_fallback. Applies to: compiler onlyJIT_GENERATE_DEBUG_INFO- Specifies whether to create debug information in output (-g) (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_LOG_VERBOSE- Generate verbose log messages (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_GENERATE_LINE_INFO- Generate line number information (-lineinfo) (0: false, default).Option type:
int. Applies to: compiler onlyJIT_CACHE_MODE- Specifies whether to enable caching explicitly (-dlcm). Choice is based on suppliedCUjit_cacheMode_enum.Option type:
unsigned intfor enumerated typeCUjit_cacheMode_enum. Applies to: compiler onlyJIT_NEW_SM3X_OPT- Used for internal purposes only, in this version of CUDA.JIT_FAST_COMPILE- Used for internal purposes only, in this version of CUDA.JIT_GLOBAL_SYMBOL_NAMES- Array of device symbol names that will be relocated to the corresponing host addresses stored inJIT_GLOBAL_SYMBOL_ADDRESSES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.Option type:
const char **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_ADDRESSES- Array of host addresses that will be used to relocate corresponding device symbols stored inJIT_GLOBAL_SYMBOL_NAMES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries.Option type:
void **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_COUNT- Number of entries inJIT_GLOBAL_SYMBOL_NAMESandJIT_GLOBAL_SYMBOL_ADDRESSESarrays.Option type:
unsigned int. Applies to: dynamic linker onlyJIT_LTO- Enable link-time optimization (-dlto) for device code (0: false, default)Option type:
int. Applies to: compiler and linkerJIT_FTZ- Control single-precision denormals (-ftz) support (0: false, default).- 1 : flushes denormal values to zero
- 0 : preserves denormal values
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_DIV- Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_SQRT- Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_FMA- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_NUM_OPTIONS- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTO
- See Also:
-
CU_JIT_FMA
public static final int CU_JIT_FMAOnline compiler and linker options. (CUjit_option)Enum values:
JIT_MAX_REGISTERS- Max number of registers that a thread may use.Option type:
unsigned int. Applies to: compiler onlyJIT_THREADS_PER_BLOCK- IN: Specifies minimum number of threads per block to target compilation forOUT: Returns the number of threads the compiler actually targeted.
This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.
Cannot be combined with
JIT_TARGET. Option type:unsigned int. Applies to: compiler onlyJIT_WALL_TIME- Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.Option type:
float. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER- Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via optionJIT_INFO_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER- Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via optionJIT_ERROR_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_OPTIMIZATION_LEVEL- Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.Option type:
unsigned int. Applies to: compiler onlyJIT_TARGET_FROM_CUCONTEXT- No option value required. Determines the target based on the current attached context (default).Option type: No option value needed. Applies to: compiler and linker
JIT_TARGET- Target is chosen based on suppliedCUjit_target. Cannot be combined withJIT_THREADS_PER_BLOCK.Option type:
unsigned intfor enumerated typeCUjit_target. Applies to: compiler and linkerJIT_FALLBACK_STRATEGY- Specifies choice of fallback strategy if matching cubin is not found.Choice is based on supplied
CUjit_fallback. This option cannot be used withcuLink*APIs as the linker requires exact matches.Option type:
unsigned intfor enumerated typeCUjit_fallback. Applies to: compiler onlyJIT_GENERATE_DEBUG_INFO- Specifies whether to create debug information in output (-g) (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_LOG_VERBOSE- Generate verbose log messages (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_GENERATE_LINE_INFO- Generate line number information (-lineinfo) (0: false, default).Option type:
int. Applies to: compiler onlyJIT_CACHE_MODE- Specifies whether to enable caching explicitly (-dlcm). Choice is based on suppliedCUjit_cacheMode_enum.Option type:
unsigned intfor enumerated typeCUjit_cacheMode_enum. Applies to: compiler onlyJIT_NEW_SM3X_OPT- Used for internal purposes only, in this version of CUDA.JIT_FAST_COMPILE- Used for internal purposes only, in this version of CUDA.JIT_GLOBAL_SYMBOL_NAMES- Array of device symbol names that will be relocated to the corresponing host addresses stored inJIT_GLOBAL_SYMBOL_ADDRESSES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.Option type:
const char **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_ADDRESSES- Array of host addresses that will be used to relocate corresponding device symbols stored inJIT_GLOBAL_SYMBOL_NAMES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries.Option type:
void **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_COUNT- Number of entries inJIT_GLOBAL_SYMBOL_NAMESandJIT_GLOBAL_SYMBOL_ADDRESSESarrays.Option type:
unsigned int. Applies to: dynamic linker onlyJIT_LTO- Enable link-time optimization (-dlto) for device code (0: false, default)Option type:
int. Applies to: compiler and linkerJIT_FTZ- Control single-precision denormals (-ftz) support (0: false, default).- 1 : flushes denormal values to zero
- 0 : preserves denormal values
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_DIV- Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_SQRT- Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_FMA- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_NUM_OPTIONS- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTO
- See Also:
-
CU_JIT_NUM_OPTIONS
public static final int CU_JIT_NUM_OPTIONSOnline compiler and linker options. (CUjit_option)Enum values:
JIT_MAX_REGISTERS- Max number of registers that a thread may use.Option type:
unsigned int. Applies to: compiler onlyJIT_THREADS_PER_BLOCK- IN: Specifies minimum number of threads per block to target compilation forOUT: Returns the number of threads the compiler actually targeted.
This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.
Cannot be combined with
JIT_TARGET. Option type:unsigned int. Applies to: compiler onlyJIT_WALL_TIME- Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.Option type:
float. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER- Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via optionJIT_INFO_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_INFO_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER- Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via optionJIT_ERROR_LOG_BUFFER_SIZE_BYTES).Option type:
char *. Applies to: compiler and linkerJIT_ERROR_LOG_BUFFER_SIZE_BYTES- IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).OUT: Amount of log buffer filled with messages.
Option type:
unsigned int. Applies to: compiler and linkerJIT_OPTIMIZATION_LEVEL- Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.Option type:
unsigned int. Applies to: compiler onlyJIT_TARGET_FROM_CUCONTEXT- No option value required. Determines the target based on the current attached context (default).Option type: No option value needed. Applies to: compiler and linker
JIT_TARGET- Target is chosen based on suppliedCUjit_target. Cannot be combined withJIT_THREADS_PER_BLOCK.Option type:
unsigned intfor enumerated typeCUjit_target. Applies to: compiler and linkerJIT_FALLBACK_STRATEGY- Specifies choice of fallback strategy if matching cubin is not found.Choice is based on supplied
CUjit_fallback. This option cannot be used withcuLink*APIs as the linker requires exact matches.Option type:
unsigned intfor enumerated typeCUjit_fallback. Applies to: compiler onlyJIT_GENERATE_DEBUG_INFO- Specifies whether to create debug information in output (-g) (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_LOG_VERBOSE- Generate verbose log messages (0: false, default).Option type:
int. Applies to: compiler and linkerJIT_GENERATE_LINE_INFO- Generate line number information (-lineinfo) (0: false, default).Option type:
int. Applies to: compiler onlyJIT_CACHE_MODE- Specifies whether to enable caching explicitly (-dlcm). Choice is based on suppliedCUjit_cacheMode_enum.Option type:
unsigned intfor enumerated typeCUjit_cacheMode_enum. Applies to: compiler onlyJIT_NEW_SM3X_OPT- Used for internal purposes only, in this version of CUDA.JIT_FAST_COMPILE- Used for internal purposes only, in this version of CUDA.JIT_GLOBAL_SYMBOL_NAMES- Array of device symbol names that will be relocated to the corresponing host addresses stored inJIT_GLOBAL_SYMBOL_ADDRESSES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.Option type:
const char **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_ADDRESSES- Array of host addresses that will be used to relocate corresponding device symbols stored inJIT_GLOBAL_SYMBOL_NAMES.Must contain
JIT_GLOBAL_SYMBOL_COUNTentries.Option type:
void **. Applies to: dynamic linker onlyJIT_GLOBAL_SYMBOL_COUNT- Number of entries inJIT_GLOBAL_SYMBOL_NAMESandJIT_GLOBAL_SYMBOL_ADDRESSESarrays.Option type:
unsigned int. Applies to: dynamic linker onlyJIT_LTO- Enable link-time optimization (-dlto) for device code (0: false, default)Option type:
int. Applies to: compiler and linkerJIT_FTZ- Control single-precision denormals (-ftz) support (0: false, default).- 1 : flushes denormal values to zero
- 0 : preserves denormal values
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_DIV- Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_PREC_SQRT- Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).- 1 : Enables the IEEE round-to-nearest mode
- 0 : Enables the fast approximation mode
Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_FMA- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTOJIT_NUM_OPTIONS- Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).Option type:
int. Applies to: link-time optimization specified withJIT_LTO
- See Also:
-
CU_TARGET_COMPUTE_20
public static final int CU_TARGET_COMPUTE_20Online compilation targets. (CUjit_target)Enum values:
TARGET_COMPUTE_20- Compute device class 2.0TARGET_COMPUTE_21- Compute device class 2.1TARGET_COMPUTE_30- Compute device class 3.0TARGET_COMPUTE_32- Compute device class 3.2TARGET_COMPUTE_35- Compute device class 3.5TARGET_COMPUTE_37- Compute device class 3.7TARGET_COMPUTE_50- Compute device class 5.0TARGET_COMPUTE_52- Compute device class 5.2TARGET_COMPUTE_53- Compute device class 5.3TARGET_COMPUTE_60- Compute device class 6.0.TARGET_COMPUTE_61- Compute device class 6.1.TARGET_COMPUTE_62- Compute device class 6.2.TARGET_COMPUTE_70- Compute device class 7.0.TARGET_COMPUTE_72- Compute device class 7.2.TARGET_COMPUTE_75- Compute device class 7.5.TARGET_COMPUTE_80- Compute device class 8.0.TARGET_COMPUTE_86- Compute device class 8.6.
- See Also:
-
CU_TARGET_COMPUTE_21
public static final int CU_TARGET_COMPUTE_21Online compilation targets. (CUjit_target)Enum values:
TARGET_COMPUTE_20- Compute device class 2.0TARGET_COMPUTE_21- Compute device class 2.1TARGET_COMPUTE_30- Compute device class 3.0TARGET_COMPUTE_32- Compute device class 3.2TARGET_COMPUTE_35- Compute device class 3.5TARGET_COMPUTE_37- Compute device class 3.7TARGET_COMPUTE_50- Compute device class 5.0TARGET_COMPUTE_52- Compute device class 5.2TARGET_COMPUTE_53- Compute device class 5.3TARGET_COMPUTE_60- Compute device class 6.0.TARGET_COMPUTE_61- Compute device class 6.1.TARGET_COMPUTE_62- Compute device class 6.2.TARGET_COMPUTE_70- Compute device class 7.0.TARGET_COMPUTE_72- Compute device class 7.2.TARGET_COMPUTE_75- Compute device class 7.5.TARGET_COMPUTE_80- Compute device class 8.0.TARGET_COMPUTE_86- Compute device class 8.6.
- See Also:
-
CU_TARGET_COMPUTE_30
public static final int CU_TARGET_COMPUTE_30Online compilation targets. (CUjit_target)Enum values:
TARGET_COMPUTE_20- Compute device class 2.0TARGET_COMPUTE_21- Compute device class 2.1TARGET_COMPUTE_30- Compute device class 3.0TARGET_COMPUTE_32- Compute device class 3.2TARGET_COMPUTE_35- Compute device class 3.5TARGET_COMPUTE_37- Compute device class 3.7TARGET_COMPUTE_50- Compute device class 5.0TARGET_COMPUTE_52- Compute device class 5.2TARGET_COMPUTE_53- Compute device class 5.3TARGET_COMPUTE_60- Compute device class 6.0.TARGET_COMPUTE_61- Compute device class 6.1.TARGET_COMPUTE_62- Compute device class 6.2.TARGET_COMPUTE_70- Compute device class 7.0.TARGET_COMPUTE_72- Compute device class 7.2.TARGET_COMPUTE_75- Compute device class 7.5.TARGET_COMPUTE_80- Compute device class 8.0.TARGET_COMPUTE_86- Compute device class 8.6.
- See Also:
-
CU_TARGET_COMPUTE_32
public static final int CU_TARGET_COMPUTE_32Online compilation targets. (CUjit_target)Enum values:
TARGET_COMPUTE_20- Compute device class 2.0TARGET_COMPUTE_21- Compute device class 2.1TARGET_COMPUTE_30- Compute device class 3.0TARGET_COMPUTE_32- Compute device class 3.2TARGET_COMPUTE_35- Compute device class 3.5TARGET_COMPUTE_37- Compute device class 3.7TARGET_COMPUTE_50- Compute device class 5.0TARGET_COMPUTE_52- Compute device class 5.2TARGET_COMPUTE_53- Compute device class 5.3TARGET_COMPUTE_60- Compute device class 6.0.TARGET_COMPUTE_61- Compute device class 6.1.TARGET_COMPUTE_62- Compute device class 6.2.TARGET_COMPUTE_70- Compute device class 7.0.TARGET_COMPUTE_72- Compute device class 7.2.TARGET_COMPUTE_75- Compute device class 7.5.TARGET_COMPUTE_80- Compute device class 8.0.TARGET_COMPUTE_86- Compute device class 8.6.
- See Also:
-
CU_TARGET_COMPUTE_35
public static final int CU_TARGET_COMPUTE_35Online compilation targets. (CUjit_target)Enum values:
TARGET_COMPUTE_20- Compute device class 2.0TARGET_COMPUTE_21- Compute device class 2.1TARGET_COMPUTE_30- Compute device class 3.0TARGET_COMPUTE_32- Compute device class 3.2TARGET_COMPUTE_35- Compute device class 3.5TARGET_COMPUTE_37- Compute device class 3.7TARGET_COMPUTE_50- Compute device class 5.0TARGET_COMPUTE_52- Compute device class 5.2TARGET_COMPUTE_53- Compute device class 5.3TARGET_COMPUTE_60- Compute device class 6.0.TARGET_COMPUTE_61- Compute device class 6.1.TARGET_COMPUTE_62- Compute device class 6.2.TARGET_COMPUTE_70- Compute device class 7.0.TARGET_COMPUTE_72- Compute device class 7.2.TARGET_COMPUTE_75- Compute device class 7.5.TARGET_COMPUTE_80- Compute device class 8.0.TARGET_COMPUTE_86- Compute device class 8.6.
- See Also:
-
CU_TARGET_COMPUTE_37
public static final int CU_TARGET_COMPUTE_37Online compilation targets. (CUjit_target)Enum values:
TARGET_COMPUTE_20- Compute device class 2.0TARGET_COMPUTE_21- Compute device class 2.1TARGET_COMPUTE_30- Compute device class 3.0TARGET_COMPUTE_32- Compute device class 3.2TARGET_COMPUTE_35- Compute device class 3.5TARGET_COMPUTE_37- Compute device class 3.7TARGET_COMPUTE_50- Compute device class 5.0TARGET_COMPUTE_52- Compute device class 5.2TARGET_COMPUTE_53- Compute device class 5.3TARGET_COMPUTE_60- Compute device class 6.0.TARGET_COMPUTE_61- Compute device class 6.1.TARGET_COMPUTE_62- Compute device class 6.2.TARGET_COMPUTE_70- Compute device class 7.0.TARGET_COMPUTE_72- Compute device class 7.2.TARGET_COMPUTE_75- Compute device class 7.5.TARGET_COMPUTE_80- Compute device class 8.0.TARGET_COMPUTE_86- Compute device class 8.6.
- See Also:
-
CU_TARGET_COMPUTE_50
public static final int CU_TARGET_COMPUTE_50Online compilation targets. (CUjit_target)Enum values:
TARGET_COMPUTE_20- Compute device class 2.0TARGET_COMPUTE_21- Compute device class 2.1TARGET_COMPUTE_30- Compute device class 3.0TARGET_COMPUTE_32- Compute device class 3.2TARGET_COMPUTE_35- Compute device class 3.5TARGET_COMPUTE_37- Compute device class 3.7TARGET_COMPUTE_50- Compute device class 5.0TARGET_COMPUTE_52- Compute device class 5.2TARGET_COMPUTE_53- Compute device class 5.3TARGET_COMPUTE_60- Compute device class 6.0.TARGET_COMPUTE_61- Compute device class 6.1.TARGET_COMPUTE_62- Compute device class 6.2.TARGET_COMPUTE_70- Compute device class 7.0.TARGET_COMPUTE_72- Compute device class 7.2.TARGET_COMPUTE_75- Compute device class 7.5.TARGET_COMPUTE_80- Compute device class 8.0.TARGET_COMPUTE_86- Compute device class 8.6.
- See Also:
-
CU_TARGET_COMPUTE_52
public static final int CU_TARGET_COMPUTE_52Online compilation targets. (CUjit_target)Enum values:
TARGET_COMPUTE_20- Compute device class 2.0TARGET_COMPUTE_21- Compute device class 2.1TARGET_COMPUTE_30- Compute device class 3.0TARGET_COMPUTE_32- Compute device class 3.2TARGET_COMPUTE_35- Compute device class 3.5TARGET_COMPUTE_37- Compute device class 3.7TARGET_COMPUTE_50- Compute device class 5.0TARGET_COMPUTE_52- Compute device class 5.2TARGET_COMPUTE_53- Compute device class 5.3TARGET_COMPUTE_60- Compute device class 6.0.TARGET_COMPUTE_61- Compute device class 6.1.TARGET_COMPUTE_62- Compute device class 6.2.TARGET_COMPUTE_70- Compute device class 7.0.TARGET_COMPUTE_72- Compute device class 7.2.TARGET_COMPUTE_75- Compute device class 7.5.TARGET_COMPUTE_80- Compute device class 8.0.TARGET_COMPUTE_86- Compute device class 8.6.
- See Also:
-
CU_TARGET_COMPUTE_53
public static final int CU_TARGET_COMPUTE_53Online compilation targets. (CUjit_target)Enum values:
TARGET_COMPUTE_20- Compute device class 2.0TARGET_COMPUTE_21- Compute device class 2.1TARGET_COMPUTE_30- Compute device class 3.0TARGET_COMPUTE_32- Compute device class 3.2TARGET_COMPUTE_35- Compute device class 3.5TARGET_COMPUTE_37- Compute device class 3.7TARGET_COMPUTE_50- Compute device class 5.0TARGET_COMPUTE_52- Compute device class 5.2TARGET_COMPUTE_53- Compute device class 5.3TARGET_COMPUTE_60- Compute device class 6.0.TARGET_COMPUTE_61- Compute device class 6.1.TARGET_COMPUTE_62- Compute device class 6.2.TARGET_COMPUTE_70- Compute device class 7.0.TARGET_COMPUTE_72- Compute device class 7.2.TARGET_COMPUTE_75- Compute device class 7.5.TARGET_COMPUTE_80- Compute device class 8.0.TARGET_COMPUTE_86- Compute device class 8.6.
- See Also:
-
CU_TARGET_COMPUTE_60
public static final int CU_TARGET_COMPUTE_60Online compilation targets. (CUjit_target)Enum values:
TARGET_COMPUTE_20- Compute device class 2.0TARGET_COMPUTE_21- Compute device class 2.1TARGET_COMPUTE_30- Compute device class 3.0TARGET_COMPUTE_32- Compute device class 3.2TARGET_COMPUTE_35- Compute device class 3.5TARGET_COMPUTE_37- Compute device class 3.7TARGET_COMPUTE_50- Compute device class 5.0TARGET_COMPUTE_52- Compute device class 5.2TARGET_COMPUTE_53- Compute device class 5.3TARGET_COMPUTE_60- Compute device class 6.0.TARGET_COMPUTE_61- Compute device class 6.1.TARGET_COMPUTE_62- Compute device class 6.2.TARGET_COMPUTE_70- Compute device class 7.0.TARGET_COMPUTE_72- Compute device class 7.2.TARGET_COMPUTE_75- Compute device class 7.5.TARGET_COMPUTE_80- Compute device class 8.0.TARGET_COMPUTE_86- Compute device class 8.6.
- See Also:
-
CU_TARGET_COMPUTE_61
public static final int CU_TARGET_COMPUTE_61Online compilation targets. (CUjit_target)Enum values:
TARGET_COMPUTE_20- Compute device class 2.0TARGET_COMPUTE_21- Compute device class 2.1TARGET_COMPUTE_30- Compute device class 3.0TARGET_COMPUTE_32- Compute device class 3.2TARGET_COMPUTE_35- Compute device class 3.5TARGET_COMPUTE_37- Compute device class 3.7TARGET_COMPUTE_50- Compute device class 5.0TARGET_COMPUTE_52- Compute device class 5.2TARGET_COMPUTE_53- Compute device class 5.3TARGET_COMPUTE_60- Compute device class 6.0.TARGET_COMPUTE_61- Compute device class 6.1.TARGET_COMPUTE_62- Compute device class 6.2.TARGET_COMPUTE_70- Compute device class 7.0.TARGET_COMPUTE_72- Compute device class 7.2.TARGET_COMPUTE_75- Compute device class 7.5.TARGET_COMPUTE_80- Compute device class 8.0.TARGET_COMPUTE_86- Compute device class 8.6.
- See Also:
-
CU_TARGET_COMPUTE_62
public static final int CU_TARGET_COMPUTE_62Online compilation targets. (CUjit_target)Enum values:
TARGET_COMPUTE_20- Compute device class 2.0TARGET_COMPUTE_21- Compute device class 2.1TARGET_COMPUTE_30- Compute device class 3.0TARGET_COMPUTE_32- Compute device class 3.2TARGET_COMPUTE_35- Compute device class 3.5TARGET_COMPUTE_37- Compute device class 3.7TARGET_COMPUTE_50- Compute device class 5.0TARGET_COMPUTE_52- Compute device class 5.2TARGET_COMPUTE_53- Compute device class 5.3TARGET_COMPUTE_60- Compute device class 6.0.TARGET_COMPUTE_61- Compute device class 6.1.TARGET_COMPUTE_62- Compute device class 6.2.TARGET_COMPUTE_70- Compute device class 7.0.TARGET_COMPUTE_72- Compute device class 7.2.TARGET_COMPUTE_75- Compute device class 7.5.TARGET_COMPUTE_80- Compute device class 8.0.TARGET_COMPUTE_86- Compute device class 8.6.
- See Also:
-
CU_TARGET_COMPUTE_70
public static final int CU_TARGET_COMPUTE_70Online compilation targets. (CUjit_target)Enum values:
TARGET_COMPUTE_20- Compute device class 2.0TARGET_COMPUTE_21- Compute device class 2.1TARGET_COMPUTE_30- Compute device class 3.0TARGET_COMPUTE_32- Compute device class 3.2TARGET_COMPUTE_35- Compute device class 3.5TARGET_COMPUTE_37- Compute device class 3.7TARGET_COMPUTE_50- Compute device class 5.0TARGET_COMPUTE_52- Compute device class 5.2TARGET_COMPUTE_53- Compute device class 5.3TARGET_COMPUTE_60- Compute device class 6.0.TARGET_COMPUTE_61- Compute device class 6.1.TARGET_COMPUTE_62- Compute device class 6.2.TARGET_COMPUTE_70- Compute device class 7.0.TARGET_COMPUTE_72- Compute device class 7.2.TARGET_COMPUTE_75- Compute device class 7.5.TARGET_COMPUTE_80- Compute device class 8.0.TARGET_COMPUTE_86- Compute device class 8.6.
- See Also:
-
CU_TARGET_COMPUTE_72
public static final int CU_TARGET_COMPUTE_72Online compilation targets. (CUjit_target)Enum values:
TARGET_COMPUTE_20- Compute device class 2.0TARGET_COMPUTE_21- Compute device class 2.1TARGET_COMPUTE_30- Compute device class 3.0TARGET_COMPUTE_32- Compute device class 3.2TARGET_COMPUTE_35- Compute device class 3.5TARGET_COMPUTE_37- Compute device class 3.7TARGET_COMPUTE_50- Compute device class 5.0TARGET_COMPUTE_52- Compute device class 5.2TARGET_COMPUTE_53- Compute device class 5.3TARGET_COMPUTE_60- Compute device class 6.0.TARGET_COMPUTE_61- Compute device class 6.1.TARGET_COMPUTE_62- Compute device class 6.2.TARGET_COMPUTE_70- Compute device class 7.0.TARGET_COMPUTE_72- Compute device class 7.2.TARGET_COMPUTE_75- Compute device class 7.5.TARGET_COMPUTE_80- Compute device class 8.0.TARGET_COMPUTE_86- Compute device class 8.6.
- See Also:
-
CU_TARGET_COMPUTE_75
public static final int CU_TARGET_COMPUTE_75Online compilation targets. (CUjit_target)Enum values:
TARGET_COMPUTE_20- Compute device class 2.0TARGET_COMPUTE_21- Compute device class 2.1TARGET_COMPUTE_30- Compute device class 3.0TARGET_COMPUTE_32- Compute device class 3.2TARGET_COMPUTE_35- Compute device class 3.5TARGET_COMPUTE_37- Compute device class 3.7TARGET_COMPUTE_50- Compute device class 5.0TARGET_COMPUTE_52- Compute device class 5.2TARGET_COMPUTE_53- Compute device class 5.3TARGET_COMPUTE_60- Compute device class 6.0.TARGET_COMPUTE_61- Compute device class 6.1.TARGET_COMPUTE_62- Compute device class 6.2.TARGET_COMPUTE_70- Compute device class 7.0.TARGET_COMPUTE_72- Compute device class 7.2.TARGET_COMPUTE_75- Compute device class 7.5.TARGET_COMPUTE_80- Compute device class 8.0.TARGET_COMPUTE_86- Compute device class 8.6.
- See Also:
-
CU_TARGET_COMPUTE_80
public static final int CU_TARGET_COMPUTE_80Online compilation targets. (CUjit_target)Enum values:
TARGET_COMPUTE_20- Compute device class 2.0TARGET_COMPUTE_21- Compute device class 2.1TARGET_COMPUTE_30- Compute device class 3.0TARGET_COMPUTE_32- Compute device class 3.2TARGET_COMPUTE_35- Compute device class 3.5TARGET_COMPUTE_37- Compute device class 3.7TARGET_COMPUTE_50- Compute device class 5.0TARGET_COMPUTE_52- Compute device class 5.2TARGET_COMPUTE_53- Compute device class 5.3TARGET_COMPUTE_60- Compute device class 6.0.TARGET_COMPUTE_61- Compute device class 6.1.TARGET_COMPUTE_62- Compute device class 6.2.TARGET_COMPUTE_70- Compute device class 7.0.TARGET_COMPUTE_72- Compute device class 7.2.TARGET_COMPUTE_75- Compute device class 7.5.TARGET_COMPUTE_80- Compute device class 8.0.TARGET_COMPUTE_86- Compute device class 8.6.
- See Also:
-
CU_TARGET_COMPUTE_86
public static final int CU_TARGET_COMPUTE_86Online compilation targets. (CUjit_target)Enum values:
TARGET_COMPUTE_20- Compute device class 2.0TARGET_COMPUTE_21- Compute device class 2.1TARGET_COMPUTE_30- Compute device class 3.0TARGET_COMPUTE_32- Compute device class 3.2TARGET_COMPUTE_35- Compute device class 3.5TARGET_COMPUTE_37- Compute device class 3.7TARGET_COMPUTE_50- Compute device class 5.0TARGET_COMPUTE_52- Compute device class 5.2TARGET_COMPUTE_53- Compute device class 5.3TARGET_COMPUTE_60- Compute device class 6.0.TARGET_COMPUTE_61- Compute device class 6.1.TARGET_COMPUTE_62- Compute device class 6.2.TARGET_COMPUTE_70- Compute device class 7.0.TARGET_COMPUTE_72- Compute device class 7.2.TARGET_COMPUTE_75- Compute device class 7.5.TARGET_COMPUTE_80- Compute device class 8.0.TARGET_COMPUTE_86- Compute device class 8.6.
- See Also:
-
CU_PREFER_PTX
public static final int CU_PREFER_PTXCubin matching fallback strategies. (CUjit_fallback)Enum values:
PREFER_PTX- Prefer to compile ptx if exact binary match not foundPREFER_BINARY- Prefer to fall back to compatible binary code if exact match not found
- See Also:
-
CU_PREFER_BINARY
public static final int CU_PREFER_BINARYCubin matching fallback strategies. (CUjit_fallback)Enum values:
PREFER_PTX- Prefer to compile ptx if exact binary match not foundPREFER_BINARY- Prefer to fall back to compatible binary code if exact match not found
- See Also:
-
CU_JIT_CACHE_OPTION_NONE
public static final int CU_JIT_CACHE_OPTION_NONECaching modes fordlcm. (CUjit_cacheMode)Enum values:
JIT_CACHE_OPTION_NONE- Compile with no -dlcm flag specifiedJIT_CACHE_OPTION_CG- Compile with L1 cache disabledJIT_CACHE_OPTION_CA- Compile with L1 cache enabled
- See Also:
-
CU_JIT_CACHE_OPTION_CG
public static final int CU_JIT_CACHE_OPTION_CGCaching modes fordlcm. (CUjit_cacheMode)Enum values:
JIT_CACHE_OPTION_NONE- Compile with no -dlcm flag specifiedJIT_CACHE_OPTION_CG- Compile with L1 cache disabledJIT_CACHE_OPTION_CA- Compile with L1 cache enabled
- See Also:
-
CU_JIT_CACHE_OPTION_CA
public static final int CU_JIT_CACHE_OPTION_CACaching modes fordlcm. (CUjit_cacheMode)Enum values:
JIT_CACHE_OPTION_NONE- Compile with no -dlcm flag specifiedJIT_CACHE_OPTION_CG- Compile with L1 cache disabledJIT_CACHE_OPTION_CA- Compile with L1 cache enabled
- See Also:
-
CU_JIT_INPUT_CUBIN
public static final int CU_JIT_INPUT_CUBINDevice code formats. (CUjitInputType)Enum values:
JIT_INPUT_CUBIN- Compiled device-class-specific device codeApplicable options: none
JIT_INPUT_PTX- PTX source code.Applicable options: PTX compiler options
JIT_INPUT_FATBINARY- Bundle of multiple cubins and/or PTX of some device code.Applicable options: PTX compiler options,
JIT_FALLBACK_STRATEGYJIT_INPUT_OBJECT- Host object with embedded device code.Applicable options: PTX compiler options,
JIT_FALLBACK_STRATEGYJIT_INPUT_LIBRARY- Archive of host objects with embedded device code.Applicable options: PTX compiler options,
JIT_FALLBACK_STRATEGYJIT_INPUT_NVVM- High-level intermediate code for link-time optimization.Applicable options: NVVM compiler options, PTX compiler options
- See Also:
-
CU_JIT_INPUT_PTX
public static final int CU_JIT_INPUT_PTXDevice code formats. (CUjitInputType)Enum values:
JIT_INPUT_CUBIN- Compiled device-class-specific device codeApplicable options: none
JIT_INPUT_PTX- PTX source code.Applicable options: PTX compiler options
JIT_INPUT_FATBINARY- Bundle of multiple cubins and/or PTX of some device code.Applicable options: PTX compiler options,
JIT_FALLBACK_STRATEGYJIT_INPUT_OBJECT- Host object with embedded device code.Applicable options: PTX compiler options,
JIT_FALLBACK_STRATEGYJIT_INPUT_LIBRARY- Archive of host objects with embedded device code.Applicable options: PTX compiler options,
JIT_FALLBACK_STRATEGYJIT_INPUT_NVVM- High-level intermediate code for link-time optimization.Applicable options: NVVM compiler options, PTX compiler options
- See Also:
-
CU_JIT_INPUT_FATBINARY
public static final int CU_JIT_INPUT_FATBINARYDevice code formats. (CUjitInputType)Enum values:
JIT_INPUT_CUBIN- Compiled device-class-specific device codeApplicable options: none
JIT_INPUT_PTX- PTX source code.Applicable options: PTX compiler options
JIT_INPUT_FATBINARY- Bundle of multiple cubins and/or PTX of some device code.Applicable options: PTX compiler options,
JIT_FALLBACK_STRATEGYJIT_INPUT_OBJECT- Host object with embedded device code.Applicable options: PTX compiler options,
JIT_FALLBACK_STRATEGYJIT_INPUT_LIBRARY- Archive of host objects with embedded device code.Applicable options: PTX compiler options,
JIT_FALLBACK_STRATEGYJIT_INPUT_NVVM- High-level intermediate code for link-time optimization.Applicable options: NVVM compiler options, PTX compiler options
- See Also:
-
CU_JIT_INPUT_OBJECT
public static final int CU_JIT_INPUT_OBJECTDevice code formats. (CUjitInputType)Enum values:
JIT_INPUT_CUBIN- Compiled device-class-specific device codeApplicable options: none
JIT_INPUT_PTX- PTX source code.Applicable options: PTX compiler options
JIT_INPUT_FATBINARY- Bundle of multiple cubins and/or PTX of some device code.Applicable options: PTX compiler options,
JIT_FALLBACK_STRATEGYJIT_INPUT_OBJECT- Host object with embedded device code.Applicable options: PTX compiler options,
JIT_FALLBACK_STRATEGYJIT_INPUT_LIBRARY- Archive of host objects with embedded device code.Applicable options: PTX compiler options,
JIT_FALLBACK_STRATEGYJIT_INPUT_NVVM- High-level intermediate code for link-time optimization.Applicable options: NVVM compiler options, PTX compiler options
- See Also:
-
CU_JIT_INPUT_LIBRARY
public static final int CU_JIT_INPUT_LIBRARYDevice code formats. (CUjitInputType)Enum values:
JIT_INPUT_CUBIN- Compiled device-class-specific device codeApplicable options: none
JIT_INPUT_PTX- PTX source code.Applicable options: PTX compiler options
JIT_INPUT_FATBINARY- Bundle of multiple cubins and/or PTX of some device code.Applicable options: PTX compiler options,
JIT_FALLBACK_STRATEGYJIT_INPUT_OBJECT- Host object with embedded device code.Applicable options: PTX compiler options,
JIT_FALLBACK_STRATEGYJIT_INPUT_LIBRARY- Archive of host objects with embedded device code.Applicable options: PTX compiler options,
JIT_FALLBACK_STRATEGYJIT_INPUT_NVVM- High-level intermediate code for link-time optimization.Applicable options: NVVM compiler options, PTX compiler options
- See Also:
-
CU_JIT_INPUT_NVVM
public static final int CU_JIT_INPUT_NVVMDevice code formats. (CUjitInputType)Enum values:
JIT_INPUT_CUBIN- Compiled device-class-specific device codeApplicable options: none
JIT_INPUT_PTX- PTX source code.Applicable options: PTX compiler options
JIT_INPUT_FATBINARY- Bundle of multiple cubins and/or PTX of some device code.Applicable options: PTX compiler options,
JIT_FALLBACK_STRATEGYJIT_INPUT_OBJECT- Host object with embedded device code.Applicable options: PTX compiler options,
JIT_FALLBACK_STRATEGYJIT_INPUT_LIBRARY- Archive of host objects with embedded device code.Applicable options: PTX compiler options,
JIT_FALLBACK_STRATEGYJIT_INPUT_NVVM- High-level intermediate code for link-time optimization.Applicable options: NVVM compiler options, PTX compiler options
- See Also:
-
CU_GRAPHICS_REGISTER_FLAGS_NONE
public static final int CU_GRAPHICS_REGISTER_FLAGS_NONEFlags to register a graphics resource. (CUgraphicsRegisterFlags)Enum values:
- See Also:
-
CU_GRAPHICS_REGISTER_FLAGS_READ_ONLY
public static final int CU_GRAPHICS_REGISTER_FLAGS_READ_ONLYFlags to register a graphics resource. (CUgraphicsRegisterFlags)Enum values:
- See Also:
-
CU_GRAPHICS_REGISTER_FLAGS_WRITE_DISCARD
public static final int CU_GRAPHICS_REGISTER_FLAGS_WRITE_DISCARDFlags to register a graphics resource. (CUgraphicsRegisterFlags)Enum values:
- See Also:
-
CU_GRAPHICS_REGISTER_FLAGS_SURFACE_LDST
public static final int CU_GRAPHICS_REGISTER_FLAGS_SURFACE_LDSTFlags to register a graphics resource. (CUgraphicsRegisterFlags)Enum values:
- See Also:
-
CU_GRAPHICS_REGISTER_FLAGS_TEXTURE_GATHER
public static final int CU_GRAPHICS_REGISTER_FLAGS_TEXTURE_GATHERFlags to register a graphics resource. (CUgraphicsRegisterFlags)Enum values:
- See Also:
-
CU_GRAPHICS_MAP_RESOURCE_FLAGS_NONE
public static final int CU_GRAPHICS_MAP_RESOURCE_FLAGS_NONEFlags for mapping and unmapping interop resources. (CUgraphicsMapResourceFlags)Enum values:
- See Also:
-
CU_GRAPHICS_MAP_RESOURCE_FLAGS_READ_ONLY
public static final int CU_GRAPHICS_MAP_RESOURCE_FLAGS_READ_ONLYFlags for mapping and unmapping interop resources. (CUgraphicsMapResourceFlags)Enum values:
- See Also:
-
CU_GRAPHICS_MAP_RESOURCE_FLAGS_WRITE_DISCARD
public static final int CU_GRAPHICS_MAP_RESOURCE_FLAGS_WRITE_DISCARDFlags for mapping and unmapping interop resources. (CUgraphicsMapResourceFlags)Enum values:
- See Also:
-
CU_CUBEMAP_FACE_POSITIVE_X
public static final int CU_CUBEMAP_FACE_POSITIVE_XArray indices for cube faces. (CUarray_cubemap_face)Enum values:
CUBEMAP_FACE_POSITIVE_X- Positive X face of cubemapCUBEMAP_FACE_NEGATIVE_X- Negative X face of cubemapCUBEMAP_FACE_POSITIVE_Y- Positive Y face of cubemapCUBEMAP_FACE_NEGATIVE_Y- Negative Y face of cubemapCUBEMAP_FACE_POSITIVE_Z- Positive Z face of cubemapCUBEMAP_FACE_NEGATIVE_Z- Negative Z face of cubemap
- See Also:
-
CU_CUBEMAP_FACE_NEGATIVE_X
public static final int CU_CUBEMAP_FACE_NEGATIVE_XArray indices for cube faces. (CUarray_cubemap_face)Enum values:
CUBEMAP_FACE_POSITIVE_X- Positive X face of cubemapCUBEMAP_FACE_NEGATIVE_X- Negative X face of cubemapCUBEMAP_FACE_POSITIVE_Y- Positive Y face of cubemapCUBEMAP_FACE_NEGATIVE_Y- Negative Y face of cubemapCUBEMAP_FACE_POSITIVE_Z- Positive Z face of cubemapCUBEMAP_FACE_NEGATIVE_Z- Negative Z face of cubemap
- See Also:
-
CU_CUBEMAP_FACE_POSITIVE_Y
public static final int CU_CUBEMAP_FACE_POSITIVE_YArray indices for cube faces. (CUarray_cubemap_face)Enum values:
CUBEMAP_FACE_POSITIVE_X- Positive X face of cubemapCUBEMAP_FACE_NEGATIVE_X- Negative X face of cubemapCUBEMAP_FACE_POSITIVE_Y- Positive Y face of cubemapCUBEMAP_FACE_NEGATIVE_Y- Negative Y face of cubemapCUBEMAP_FACE_POSITIVE_Z- Positive Z face of cubemapCUBEMAP_FACE_NEGATIVE_Z- Negative Z face of cubemap
- See Also:
-
CU_CUBEMAP_FACE_NEGATIVE_Y
public static final int CU_CUBEMAP_FACE_NEGATIVE_YArray indices for cube faces. (CUarray_cubemap_face)Enum values:
CUBEMAP_FACE_POSITIVE_X- Positive X face of cubemapCUBEMAP_FACE_NEGATIVE_X- Negative X face of cubemapCUBEMAP_FACE_POSITIVE_Y- Positive Y face of cubemapCUBEMAP_FACE_NEGATIVE_Y- Negative Y face of cubemapCUBEMAP_FACE_POSITIVE_Z- Positive Z face of cubemapCUBEMAP_FACE_NEGATIVE_Z- Negative Z face of cubemap
- See Also:
-
CU_CUBEMAP_FACE_POSITIVE_Z
public static final int CU_CUBEMAP_FACE_POSITIVE_ZArray indices for cube faces. (CUarray_cubemap_face)Enum values:
CUBEMAP_FACE_POSITIVE_X- Positive X face of cubemapCUBEMAP_FACE_NEGATIVE_X- Negative X face of cubemapCUBEMAP_FACE_POSITIVE_Y- Positive Y face of cubemapCUBEMAP_FACE_NEGATIVE_Y- Negative Y face of cubemapCUBEMAP_FACE_POSITIVE_Z- Positive Z face of cubemapCUBEMAP_FACE_NEGATIVE_Z- Negative Z face of cubemap
- See Also:
-
CU_CUBEMAP_FACE_NEGATIVE_Z
public static final int CU_CUBEMAP_FACE_NEGATIVE_ZArray indices for cube faces. (CUarray_cubemap_face)Enum values:
CUBEMAP_FACE_POSITIVE_X- Positive X face of cubemapCUBEMAP_FACE_NEGATIVE_X- Negative X face of cubemapCUBEMAP_FACE_POSITIVE_Y- Positive Y face of cubemapCUBEMAP_FACE_NEGATIVE_Y- Negative Y face of cubemapCUBEMAP_FACE_POSITIVE_Z- Positive Z face of cubemapCUBEMAP_FACE_NEGATIVE_Z- Negative Z face of cubemap
- See Also:
-
CU_LIMIT_STACK_SIZE
public static final int CU_LIMIT_STACK_SIZELimits. (CUlimit)Enum values:
LIMIT_STACK_SIZE- GPU thread stack sizeLIMIT_PRINTF_FIFO_SIZE- GPU printf FIFO sizeLIMIT_MALLOC_HEAP_SIZE- GPU malloc heap sizeLIMIT_DEV_RUNTIME_SYNC_DEPTH- GPU device runtime launch synchronize depthLIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT- GPU device runtime pending launch countLIMIT_MAX_L2_FETCH_GRANULARITY- A value between 0 and 128 that indicates the maximum fetch granularity of L2 (in Bytes). This is a hintLIMIT_PERSISTING_L2_CACHE_SIZE- A size in bytes for L2 persisting lines cache size
- See Also:
-
CU_LIMIT_PRINTF_FIFO_SIZE
public static final int CU_LIMIT_PRINTF_FIFO_SIZELimits. (CUlimit)Enum values:
LIMIT_STACK_SIZE- GPU thread stack sizeLIMIT_PRINTF_FIFO_SIZE- GPU printf FIFO sizeLIMIT_MALLOC_HEAP_SIZE- GPU malloc heap sizeLIMIT_DEV_RUNTIME_SYNC_DEPTH- GPU device runtime launch synchronize depthLIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT- GPU device runtime pending launch countLIMIT_MAX_L2_FETCH_GRANULARITY- A value between 0 and 128 that indicates the maximum fetch granularity of L2 (in Bytes). This is a hintLIMIT_PERSISTING_L2_CACHE_SIZE- A size in bytes for L2 persisting lines cache size
- See Also:
-
CU_LIMIT_MALLOC_HEAP_SIZE
public static final int CU_LIMIT_MALLOC_HEAP_SIZELimits. (CUlimit)Enum values:
LIMIT_STACK_SIZE- GPU thread stack sizeLIMIT_PRINTF_FIFO_SIZE- GPU printf FIFO sizeLIMIT_MALLOC_HEAP_SIZE- GPU malloc heap sizeLIMIT_DEV_RUNTIME_SYNC_DEPTH- GPU device runtime launch synchronize depthLIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT- GPU device runtime pending launch countLIMIT_MAX_L2_FETCH_GRANULARITY- A value between 0 and 128 that indicates the maximum fetch granularity of L2 (in Bytes). This is a hintLIMIT_PERSISTING_L2_CACHE_SIZE- A size in bytes for L2 persisting lines cache size
- See Also:
-
CU_LIMIT_DEV_RUNTIME_SYNC_DEPTH
public static final int CU_LIMIT_DEV_RUNTIME_SYNC_DEPTHLimits. (CUlimit)Enum values:
LIMIT_STACK_SIZE- GPU thread stack sizeLIMIT_PRINTF_FIFO_SIZE- GPU printf FIFO sizeLIMIT_MALLOC_HEAP_SIZE- GPU malloc heap sizeLIMIT_DEV_RUNTIME_SYNC_DEPTH- GPU device runtime launch synchronize depthLIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT- GPU device runtime pending launch countLIMIT_MAX_L2_FETCH_GRANULARITY- A value between 0 and 128 that indicates the maximum fetch granularity of L2 (in Bytes). This is a hintLIMIT_PERSISTING_L2_CACHE_SIZE- A size in bytes for L2 persisting lines cache size
- See Also:
-
CU_LIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT
public static final int CU_LIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNTLimits. (CUlimit)Enum values:
LIMIT_STACK_SIZE- GPU thread stack sizeLIMIT_PRINTF_FIFO_SIZE- GPU printf FIFO sizeLIMIT_MALLOC_HEAP_SIZE- GPU malloc heap sizeLIMIT_DEV_RUNTIME_SYNC_DEPTH- GPU device runtime launch synchronize depthLIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT- GPU device runtime pending launch countLIMIT_MAX_L2_FETCH_GRANULARITY- A value between 0 and 128 that indicates the maximum fetch granularity of L2 (in Bytes). This is a hintLIMIT_PERSISTING_L2_CACHE_SIZE- A size in bytes for L2 persisting lines cache size
- See Also:
-
CU_LIMIT_MAX_L2_FETCH_GRANULARITY
public static final int CU_LIMIT_MAX_L2_FETCH_GRANULARITYLimits. (CUlimit)Enum values:
LIMIT_STACK_SIZE- GPU thread stack sizeLIMIT_PRINTF_FIFO_SIZE- GPU printf FIFO sizeLIMIT_MALLOC_HEAP_SIZE- GPU malloc heap sizeLIMIT_DEV_RUNTIME_SYNC_DEPTH- GPU device runtime launch synchronize depthLIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT- GPU device runtime pending launch countLIMIT_MAX_L2_FETCH_GRANULARITY- A value between 0 and 128 that indicates the maximum fetch granularity of L2 (in Bytes). This is a hintLIMIT_PERSISTING_L2_CACHE_SIZE- A size in bytes for L2 persisting lines cache size
- See Also:
-
CU_LIMIT_PERSISTING_L2_CACHE_SIZE
public static final int CU_LIMIT_PERSISTING_L2_CACHE_SIZELimits. (CUlimit)Enum values:
LIMIT_STACK_SIZE- GPU thread stack sizeLIMIT_PRINTF_FIFO_SIZE- GPU printf FIFO sizeLIMIT_MALLOC_HEAP_SIZE- GPU malloc heap sizeLIMIT_DEV_RUNTIME_SYNC_DEPTH- GPU device runtime launch synchronize depthLIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT- GPU device runtime pending launch countLIMIT_MAX_L2_FETCH_GRANULARITY- A value between 0 and 128 that indicates the maximum fetch granularity of L2 (in Bytes). This is a hintLIMIT_PERSISTING_L2_CACHE_SIZE- A size in bytes for L2 persisting lines cache size
- See Also:
-
CU_RESOURCE_TYPE_ARRAY
public static final int CU_RESOURCE_TYPE_ARRAYResource types. (CUresourcetype)Enum values:
RESOURCE_TYPE_ARRAY- Array resoureRESOURCE_TYPE_MIPMAPPED_ARRAY- Mipmapped array resourceRESOURCE_TYPE_LINEAR- Linear resourceRESOURCE_TYPE_PITCH2D- Pitch 2D resource
- See Also:
-
CU_RESOURCE_TYPE_MIPMAPPED_ARRAY
public static final int CU_RESOURCE_TYPE_MIPMAPPED_ARRAYResource types. (CUresourcetype)Enum values:
RESOURCE_TYPE_ARRAY- Array resoureRESOURCE_TYPE_MIPMAPPED_ARRAY- Mipmapped array resourceRESOURCE_TYPE_LINEAR- Linear resourceRESOURCE_TYPE_PITCH2D- Pitch 2D resource
- See Also:
-
CU_RESOURCE_TYPE_LINEAR
public static final int CU_RESOURCE_TYPE_LINEARResource types. (CUresourcetype)Enum values:
RESOURCE_TYPE_ARRAY- Array resoureRESOURCE_TYPE_MIPMAPPED_ARRAY- Mipmapped array resourceRESOURCE_TYPE_LINEAR- Linear resourceRESOURCE_TYPE_PITCH2D- Pitch 2D resource
- See Also:
-
CU_RESOURCE_TYPE_PITCH2D
public static final int CU_RESOURCE_TYPE_PITCH2DResource types. (CUresourcetype)Enum values:
RESOURCE_TYPE_ARRAY- Array resoureRESOURCE_TYPE_MIPMAPPED_ARRAY- Mipmapped array resourceRESOURCE_TYPE_LINEAR- Linear resourceRESOURCE_TYPE_PITCH2D- Pitch 2D resource
- See Also:
-
CU_ACCESS_PROPERTY_NORMAL
public static final int CU_ACCESS_PROPERTY_NORMALSpecifies performance hint withCUaccessPolicyWindowforhitPropandmissPropmembers. (CUaccessProperty)Enum values:
ACCESS_PROPERTY_NORMAL- Normal cache persistence.ACCESS_PROPERTY_STREAMING- Streaming access is less likely to persit from cache.ACCESS_PROPERTY_PERSISTING- Persisting access is more likely to persist in cache.
- See Also:
-
CU_ACCESS_PROPERTY_STREAMING
public static final int CU_ACCESS_PROPERTY_STREAMINGSpecifies performance hint withCUaccessPolicyWindowforhitPropandmissPropmembers. (CUaccessProperty)Enum values:
ACCESS_PROPERTY_NORMAL- Normal cache persistence.ACCESS_PROPERTY_STREAMING- Streaming access is less likely to persit from cache.ACCESS_PROPERTY_PERSISTING- Persisting access is more likely to persist in cache.
- See Also:
-
CU_ACCESS_PROPERTY_PERSISTING
public static final int CU_ACCESS_PROPERTY_PERSISTINGSpecifies performance hint withCUaccessPolicyWindowforhitPropandmissPropmembers. (CUaccessProperty)Enum values:
ACCESS_PROPERTY_NORMAL- Normal cache persistence.ACCESS_PROPERTY_STREAMING- Streaming access is less likely to persit from cache.ACCESS_PROPERTY_PERSISTING- Persisting access is more likely to persist in cache.
- See Also:
-
CU_GRAPH_NODE_TYPE_KERNEL
public static final int CU_GRAPH_NODE_TYPE_KERNELGraph node types. (CUgraphNodeType)Enum values:
GRAPH_NODE_TYPE_KERNEL- GPU kernel nodeGRAPH_NODE_TYPE_MEMCPY- Memcpy nodeGRAPH_NODE_TYPE_MEMSET- Memset nodeGRAPH_NODE_TYPE_HOST- Host (executable) nodeGRAPH_NODE_TYPE_GRAPH- Node which executes an embedded graphGRAPH_NODE_TYPE_EMPTY- Empty (no-op) nodeGRAPH_NODE_TYPE_WAIT_EVENT- External event wait nodeGRAPH_NODE_TYPE_EVENT_RECORD- External event record nodeGRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL- External semaphore signal nodeGRAPH_NODE_TYPE_EXT_SEMAS_WAIT- External semaphore wait nodeGRAPH_NODE_TYPE_MEM_ALLOC- Memory Allocation NodeGRAPH_NODE_TYPE_MEM_FREE- Memory Free Node
- See Also:
-
CU_GRAPH_NODE_TYPE_MEMCPY
public static final int CU_GRAPH_NODE_TYPE_MEMCPYGraph node types. (CUgraphNodeType)Enum values:
GRAPH_NODE_TYPE_KERNEL- GPU kernel nodeGRAPH_NODE_TYPE_MEMCPY- Memcpy nodeGRAPH_NODE_TYPE_MEMSET- Memset nodeGRAPH_NODE_TYPE_HOST- Host (executable) nodeGRAPH_NODE_TYPE_GRAPH- Node which executes an embedded graphGRAPH_NODE_TYPE_EMPTY- Empty (no-op) nodeGRAPH_NODE_TYPE_WAIT_EVENT- External event wait nodeGRAPH_NODE_TYPE_EVENT_RECORD- External event record nodeGRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL- External semaphore signal nodeGRAPH_NODE_TYPE_EXT_SEMAS_WAIT- External semaphore wait nodeGRAPH_NODE_TYPE_MEM_ALLOC- Memory Allocation NodeGRAPH_NODE_TYPE_MEM_FREE- Memory Free Node
- See Also:
-
CU_GRAPH_NODE_TYPE_MEMSET
public static final int CU_GRAPH_NODE_TYPE_MEMSETGraph node types. (CUgraphNodeType)Enum values:
GRAPH_NODE_TYPE_KERNEL- GPU kernel nodeGRAPH_NODE_TYPE_MEMCPY- Memcpy nodeGRAPH_NODE_TYPE_MEMSET- Memset nodeGRAPH_NODE_TYPE_HOST- Host (executable) nodeGRAPH_NODE_TYPE_GRAPH- Node which executes an embedded graphGRAPH_NODE_TYPE_EMPTY- Empty (no-op) nodeGRAPH_NODE_TYPE_WAIT_EVENT- External event wait nodeGRAPH_NODE_TYPE_EVENT_RECORD- External event record nodeGRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL- External semaphore signal nodeGRAPH_NODE_TYPE_EXT_SEMAS_WAIT- External semaphore wait nodeGRAPH_NODE_TYPE_MEM_ALLOC- Memory Allocation NodeGRAPH_NODE_TYPE_MEM_FREE- Memory Free Node
- See Also:
-
CU_GRAPH_NODE_TYPE_HOST
public static final int CU_GRAPH_NODE_TYPE_HOSTGraph node types. (CUgraphNodeType)Enum values:
GRAPH_NODE_TYPE_KERNEL- GPU kernel nodeGRAPH_NODE_TYPE_MEMCPY- Memcpy nodeGRAPH_NODE_TYPE_MEMSET- Memset nodeGRAPH_NODE_TYPE_HOST- Host (executable) nodeGRAPH_NODE_TYPE_GRAPH- Node which executes an embedded graphGRAPH_NODE_TYPE_EMPTY- Empty (no-op) nodeGRAPH_NODE_TYPE_WAIT_EVENT- External event wait nodeGRAPH_NODE_TYPE_EVENT_RECORD- External event record nodeGRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL- External semaphore signal nodeGRAPH_NODE_TYPE_EXT_SEMAS_WAIT- External semaphore wait nodeGRAPH_NODE_TYPE_MEM_ALLOC- Memory Allocation NodeGRAPH_NODE_TYPE_MEM_FREE- Memory Free Node
- See Also:
-
CU_GRAPH_NODE_TYPE_GRAPH
public static final int CU_GRAPH_NODE_TYPE_GRAPHGraph node types. (CUgraphNodeType)Enum values:
GRAPH_NODE_TYPE_KERNEL- GPU kernel nodeGRAPH_NODE_TYPE_MEMCPY- Memcpy nodeGRAPH_NODE_TYPE_MEMSET- Memset nodeGRAPH_NODE_TYPE_HOST- Host (executable) nodeGRAPH_NODE_TYPE_GRAPH- Node which executes an embedded graphGRAPH_NODE_TYPE_EMPTY- Empty (no-op) nodeGRAPH_NODE_TYPE_WAIT_EVENT- External event wait nodeGRAPH_NODE_TYPE_EVENT_RECORD- External event record nodeGRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL- External semaphore signal nodeGRAPH_NODE_TYPE_EXT_SEMAS_WAIT- External semaphore wait nodeGRAPH_NODE_TYPE_MEM_ALLOC- Memory Allocation NodeGRAPH_NODE_TYPE_MEM_FREE- Memory Free Node
- See Also:
-
CU_GRAPH_NODE_TYPE_EMPTY
public static final int CU_GRAPH_NODE_TYPE_EMPTYGraph node types. (CUgraphNodeType)Enum values:
GRAPH_NODE_TYPE_KERNEL- GPU kernel nodeGRAPH_NODE_TYPE_MEMCPY- Memcpy nodeGRAPH_NODE_TYPE_MEMSET- Memset nodeGRAPH_NODE_TYPE_HOST- Host (executable) nodeGRAPH_NODE_TYPE_GRAPH- Node which executes an embedded graphGRAPH_NODE_TYPE_EMPTY- Empty (no-op) nodeGRAPH_NODE_TYPE_WAIT_EVENT- External event wait nodeGRAPH_NODE_TYPE_EVENT_RECORD- External event record nodeGRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL- External semaphore signal nodeGRAPH_NODE_TYPE_EXT_SEMAS_WAIT- External semaphore wait nodeGRAPH_NODE_TYPE_MEM_ALLOC- Memory Allocation NodeGRAPH_NODE_TYPE_MEM_FREE- Memory Free Node
- See Also:
-
CU_GRAPH_NODE_TYPE_WAIT_EVENT
public static final int CU_GRAPH_NODE_TYPE_WAIT_EVENTGraph node types. (CUgraphNodeType)Enum values:
GRAPH_NODE_TYPE_KERNEL- GPU kernel nodeGRAPH_NODE_TYPE_MEMCPY- Memcpy nodeGRAPH_NODE_TYPE_MEMSET- Memset nodeGRAPH_NODE_TYPE_HOST- Host (executable) nodeGRAPH_NODE_TYPE_GRAPH- Node which executes an embedded graphGRAPH_NODE_TYPE_EMPTY- Empty (no-op) nodeGRAPH_NODE_TYPE_WAIT_EVENT- External event wait nodeGRAPH_NODE_TYPE_EVENT_RECORD- External event record nodeGRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL- External semaphore signal nodeGRAPH_NODE_TYPE_EXT_SEMAS_WAIT- External semaphore wait nodeGRAPH_NODE_TYPE_MEM_ALLOC- Memory Allocation NodeGRAPH_NODE_TYPE_MEM_FREE- Memory Free Node
- See Also:
-
CU_GRAPH_NODE_TYPE_EVENT_RECORD
public static final int CU_GRAPH_NODE_TYPE_EVENT_RECORDGraph node types. (CUgraphNodeType)Enum values:
GRAPH_NODE_TYPE_KERNEL- GPU kernel nodeGRAPH_NODE_TYPE_MEMCPY- Memcpy nodeGRAPH_NODE_TYPE_MEMSET- Memset nodeGRAPH_NODE_TYPE_HOST- Host (executable) nodeGRAPH_NODE_TYPE_GRAPH- Node which executes an embedded graphGRAPH_NODE_TYPE_EMPTY- Empty (no-op) nodeGRAPH_NODE_TYPE_WAIT_EVENT- External event wait nodeGRAPH_NODE_TYPE_EVENT_RECORD- External event record nodeGRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL- External semaphore signal nodeGRAPH_NODE_TYPE_EXT_SEMAS_WAIT- External semaphore wait nodeGRAPH_NODE_TYPE_MEM_ALLOC- Memory Allocation NodeGRAPH_NODE_TYPE_MEM_FREE- Memory Free Node
- See Also:
-
CU_GRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL
public static final int CU_GRAPH_NODE_TYPE_EXT_SEMAS_SIGNALGraph node types. (CUgraphNodeType)Enum values:
GRAPH_NODE_TYPE_KERNEL- GPU kernel nodeGRAPH_NODE_TYPE_MEMCPY- Memcpy nodeGRAPH_NODE_TYPE_MEMSET- Memset nodeGRAPH_NODE_TYPE_HOST- Host (executable) nodeGRAPH_NODE_TYPE_GRAPH- Node which executes an embedded graphGRAPH_NODE_TYPE_EMPTY- Empty (no-op) nodeGRAPH_NODE_TYPE_WAIT_EVENT- External event wait nodeGRAPH_NODE_TYPE_EVENT_RECORD- External event record nodeGRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL- External semaphore signal nodeGRAPH_NODE_TYPE_EXT_SEMAS_WAIT- External semaphore wait nodeGRAPH_NODE_TYPE_MEM_ALLOC- Memory Allocation NodeGRAPH_NODE_TYPE_MEM_FREE- Memory Free Node
- See Also:
-
CU_GRAPH_NODE_TYPE_EXT_SEMAS_WAIT
public static final int CU_GRAPH_NODE_TYPE_EXT_SEMAS_WAITGraph node types. (CUgraphNodeType)Enum values:
GRAPH_NODE_TYPE_KERNEL- GPU kernel nodeGRAPH_NODE_TYPE_MEMCPY- Memcpy nodeGRAPH_NODE_TYPE_MEMSET- Memset nodeGRAPH_NODE_TYPE_HOST- Host (executable) nodeGRAPH_NODE_TYPE_GRAPH- Node which executes an embedded graphGRAPH_NODE_TYPE_EMPTY- Empty (no-op) nodeGRAPH_NODE_TYPE_WAIT_EVENT- External event wait nodeGRAPH_NODE_TYPE_EVENT_RECORD- External event record nodeGRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL- External semaphore signal nodeGRAPH_NODE_TYPE_EXT_SEMAS_WAIT- External semaphore wait nodeGRAPH_NODE_TYPE_MEM_ALLOC- Memory Allocation NodeGRAPH_NODE_TYPE_MEM_FREE- Memory Free Node
- See Also:
-
CU_GRAPH_NODE_TYPE_MEM_ALLOC
public static final int CU_GRAPH_NODE_TYPE_MEM_ALLOCGraph node types. (CUgraphNodeType)Enum values:
GRAPH_NODE_TYPE_KERNEL- GPU kernel nodeGRAPH_NODE_TYPE_MEMCPY- Memcpy nodeGRAPH_NODE_TYPE_MEMSET- Memset nodeGRAPH_NODE_TYPE_HOST- Host (executable) nodeGRAPH_NODE_TYPE_GRAPH- Node which executes an embedded graphGRAPH_NODE_TYPE_EMPTY- Empty (no-op) nodeGRAPH_NODE_TYPE_WAIT_EVENT- External event wait nodeGRAPH_NODE_TYPE_EVENT_RECORD- External event record nodeGRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL- External semaphore signal nodeGRAPH_NODE_TYPE_EXT_SEMAS_WAIT- External semaphore wait nodeGRAPH_NODE_TYPE_MEM_ALLOC- Memory Allocation NodeGRAPH_NODE_TYPE_MEM_FREE- Memory Free Node
- See Also:
-
CU_GRAPH_NODE_TYPE_MEM_FREE
public static final int CU_GRAPH_NODE_TYPE_MEM_FREEGraph node types. (CUgraphNodeType)Enum values:
GRAPH_NODE_TYPE_KERNEL- GPU kernel nodeGRAPH_NODE_TYPE_MEMCPY- Memcpy nodeGRAPH_NODE_TYPE_MEMSET- Memset nodeGRAPH_NODE_TYPE_HOST- Host (executable) nodeGRAPH_NODE_TYPE_GRAPH- Node which executes an embedded graphGRAPH_NODE_TYPE_EMPTY- Empty (no-op) nodeGRAPH_NODE_TYPE_WAIT_EVENT- External event wait nodeGRAPH_NODE_TYPE_EVENT_RECORD- External event record nodeGRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL- External semaphore signal nodeGRAPH_NODE_TYPE_EXT_SEMAS_WAIT- External semaphore wait nodeGRAPH_NODE_TYPE_MEM_ALLOC- Memory Allocation NodeGRAPH_NODE_TYPE_MEM_FREE- Memory Free Node
- See Also:
-
CU_SYNC_POLICY_AUTO
public static final int CU_SYNC_POLICY_AUTOCUsynchronizationPolicyEnum values:
- See Also:
-
CU_SYNC_POLICY_SPIN
public static final int CU_SYNC_POLICY_SPINCUsynchronizationPolicyEnum values:
- See Also:
-
CU_SYNC_POLICY_YIELD
public static final int CU_SYNC_POLICY_YIELDCUsynchronizationPolicyEnum values:
- See Also:
-
CU_SYNC_POLICY_BLOCKING_SYNC
public static final int CU_SYNC_POLICY_BLOCKING_SYNCCUsynchronizationPolicyEnum values:
- See Also:
-
CU_KERNEL_NODE_ATTRIBUTE_ACCESS_POLICY_WINDOW
public static final int CU_KERNEL_NODE_ATTRIBUTE_ACCESS_POLICY_WINDOWGraph kernel node Attributes (CUkernelNodeAttrID)Enum values:
KERNEL_NODE_ATTRIBUTE_ACCESS_POLICY_WINDOW- Identifier forCUkernelNodeAttrValue{@code accessPolicyWindow}.KERNEL_NODE_ATTRIBUTE_COOPERATIVE- Allows a kernel node to be cooperative (seeLaunchCooperativeKernel).
- See Also:
-
CU_KERNEL_NODE_ATTRIBUTE_COOPERATIVE
public static final int CU_KERNEL_NODE_ATTRIBUTE_COOPERATIVEGraph kernel node Attributes (CUkernelNodeAttrID)Enum values:
KERNEL_NODE_ATTRIBUTE_ACCESS_POLICY_WINDOW- Identifier forCUkernelNodeAttrValue{@code accessPolicyWindow}.KERNEL_NODE_ATTRIBUTE_COOPERATIVE- Allows a kernel node to be cooperative (seeLaunchCooperativeKernel).
- See Also:
-
CU_STREAM_CAPTURE_STATUS_NONE
public static final int CU_STREAM_CAPTURE_STATUS_NONEPossible stream capture statuses returned byStreamIsCapturing. (CUstreamCaptureStatus)Enum values:
STREAM_CAPTURE_STATUS_NONE- Stream is not capturingSTREAM_CAPTURE_STATUS_ACTIVE- Stream is actively capturingSTREAM_CAPTURE_STATUS_INVALIDATED- Stream is part of a capture sequence that has been invalidated, but not terminated
- See Also:
-
CU_STREAM_CAPTURE_STATUS_ACTIVE
public static final int CU_STREAM_CAPTURE_STATUS_ACTIVEPossible stream capture statuses returned byStreamIsCapturing. (CUstreamCaptureStatus)Enum values:
STREAM_CAPTURE_STATUS_NONE- Stream is not capturingSTREAM_CAPTURE_STATUS_ACTIVE- Stream is actively capturingSTREAM_CAPTURE_STATUS_INVALIDATED- Stream is part of a capture sequence that has been invalidated, but not terminated
- See Also:
-
CU_STREAM_CAPTURE_STATUS_INVALIDATED
public static final int CU_STREAM_CAPTURE_STATUS_INVALIDATEDPossible stream capture statuses returned byStreamIsCapturing. (CUstreamCaptureStatus)Enum values:
STREAM_CAPTURE_STATUS_NONE- Stream is not capturingSTREAM_CAPTURE_STATUS_ACTIVE- Stream is actively capturingSTREAM_CAPTURE_STATUS_INVALIDATED- Stream is part of a capture sequence that has been invalidated, but not terminated
- See Also:
-
CU_STREAM_CAPTURE_MODE_GLOBAL
public static final int CU_STREAM_CAPTURE_MODE_GLOBALPossible modes for stream capture thread interactions. (CUstreamCaptureMode)For more details see
StreamBeginCaptureandThreadExchangeStreamCaptureModeEnum values:
- See Also:
-
CU_STREAM_CAPTURE_MODE_THREAD_LOCAL
public static final int CU_STREAM_CAPTURE_MODE_THREAD_LOCALPossible modes for stream capture thread interactions. (CUstreamCaptureMode)For more details see
StreamBeginCaptureandThreadExchangeStreamCaptureModeEnum values:
- See Also:
-
CU_STREAM_CAPTURE_MODE_RELAXED
public static final int CU_STREAM_CAPTURE_MODE_RELAXEDPossible modes for stream capture thread interactions. (CUstreamCaptureMode)For more details see
StreamBeginCaptureandThreadExchangeStreamCaptureModeEnum values:
- See Also:
-
CU_STREAM_ATTRIBUTE_ACCESS_POLICY_WINDOW
public static final int CU_STREAM_ATTRIBUTE_ACCESS_POLICY_WINDOWStream Attributes (CUstreamAttrID)Enum values:
STREAM_ATTRIBUTE_ACCESS_POLICY_WINDOW- Identifier forCUstreamAttrValue{@code accessPolicyWindow}.STREAM_ATTRIBUTE_SYNCHRONIZATION_POLICY-CUsynchronizationPolicyfor work queued up in this stream
- See Also:
-
CU_STREAM_ATTRIBUTE_SYNCHRONIZATION_POLICY
public static final int CU_STREAM_ATTRIBUTE_SYNCHRONIZATION_POLICYStream Attributes (CUstreamAttrID)Enum values:
STREAM_ATTRIBUTE_ACCESS_POLICY_WINDOW- Identifier forCUstreamAttrValue{@code accessPolicyWindow}.STREAM_ATTRIBUTE_SYNCHRONIZATION_POLICY-CUsynchronizationPolicyfor work queued up in this stream
- See Also:
-
CU_GET_PROC_ADDRESS_DEFAULT
public static final int CU_GET_PROC_ADDRESS_DEFAULTFlags to specify search options. For more details seeGetProcAddress. (CUdriverProcAddress_flags)Enum values:
GET_PROC_ADDRESS_DEFAULT- Default search mode for driver symbols.GET_PROC_ADDRESS_LEGACY_STREAM- Search for legacy versions of driver symbols.GET_PROC_ADDRESS_PER_THREAD_DEFAULT_STREAM- Search for per-thread versions of driver symbols.
- See Also:
-
CU_GET_PROC_ADDRESS_LEGACY_STREAM
public static final int CU_GET_PROC_ADDRESS_LEGACY_STREAMFlags to specify search options. For more details seeGetProcAddress. (CUdriverProcAddress_flags)Enum values:
GET_PROC_ADDRESS_DEFAULT- Default search mode for driver symbols.GET_PROC_ADDRESS_LEGACY_STREAM- Search for legacy versions of driver symbols.GET_PROC_ADDRESS_PER_THREAD_DEFAULT_STREAM- Search for per-thread versions of driver symbols.
- See Also:
-
CU_GET_PROC_ADDRESS_PER_THREAD_DEFAULT_STREAM
public static final int CU_GET_PROC_ADDRESS_PER_THREAD_DEFAULT_STREAMFlags to specify search options. For more details seeGetProcAddress. (CUdriverProcAddress_flags)Enum values:
GET_PROC_ADDRESS_DEFAULT- Default search mode for driver symbols.GET_PROC_ADDRESS_LEGACY_STREAM- Search for legacy versions of driver symbols.GET_PROC_ADDRESS_PER_THREAD_DEFAULT_STREAM- Search for per-thread versions of driver symbols.
- See Also:
-
CU_EXEC_AFFINITY_TYPE_SM_COUNT
public static final int CU_EXEC_AFFINITY_TYPE_SM_COUNTExecution Affinity Types(
CUexecAffinityType)Enum values:
EXEC_AFFINITY_TYPE_SM_COUNT- Create a context with limited SMs.EXEC_AFFINITY_TYPE_MAX
- See Also:
-
CU_EXEC_AFFINITY_TYPE_MAX
public static final int CU_EXEC_AFFINITY_TYPE_MAXExecution Affinity Types(
CUexecAffinityType)Enum values:
EXEC_AFFINITY_TYPE_SM_COUNT- Create a context with limited SMs.EXEC_AFFINITY_TYPE_MAX
- See Also:
-
CUDA_SUCCESS
public static final int CUDA_SUCCESSError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_INVALID_VALUE
public static final int CUDA_ERROR_INVALID_VALUEError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_OUT_OF_MEMORY
public static final int CUDA_ERROR_OUT_OF_MEMORYError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_NOT_INITIALIZED
public static final int CUDA_ERROR_NOT_INITIALIZEDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_DEINITIALIZED
public static final int CUDA_ERROR_DEINITIALIZEDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_PROFILER_DISABLED
public static final int CUDA_ERROR_PROFILER_DISABLEDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_PROFILER_NOT_INITIALIZED
public static final int CUDA_ERROR_PROFILER_NOT_INITIALIZEDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_PROFILER_ALREADY_STARTED
public static final int CUDA_ERROR_PROFILER_ALREADY_STARTEDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_PROFILER_ALREADY_STOPPED
public static final int CUDA_ERROR_PROFILER_ALREADY_STOPPEDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_STUB_LIBRARY
public static final int CUDA_ERROR_STUB_LIBRARYError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_NO_DEVICE
public static final int CUDA_ERROR_NO_DEVICEError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_INVALID_DEVICE
public static final int CUDA_ERROR_INVALID_DEVICEError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_DEVICE_NOT_LICENSED
public static final int CUDA_ERROR_DEVICE_NOT_LICENSEDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_INVALID_IMAGE
public static final int CUDA_ERROR_INVALID_IMAGEError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_INVALID_CONTEXT
public static final int CUDA_ERROR_INVALID_CONTEXTError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_CONTEXT_ALREADY_CURRENT
public static final int CUDA_ERROR_CONTEXT_ALREADY_CURRENTError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_MAP_FAILED
public static final int CUDA_ERROR_MAP_FAILEDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_UNMAP_FAILED
public static final int CUDA_ERROR_UNMAP_FAILEDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_ARRAY_IS_MAPPED
public static final int CUDA_ERROR_ARRAY_IS_MAPPEDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_ALREADY_MAPPED
public static final int CUDA_ERROR_ALREADY_MAPPEDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_NO_BINARY_FOR_GPU
public static final int CUDA_ERROR_NO_BINARY_FOR_GPUError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_ALREADY_ACQUIRED
public static final int CUDA_ERROR_ALREADY_ACQUIREDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_NOT_MAPPED
public static final int CUDA_ERROR_NOT_MAPPEDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_NOT_MAPPED_AS_ARRAY
public static final int CUDA_ERROR_NOT_MAPPED_AS_ARRAYError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_NOT_MAPPED_AS_POINTER
public static final int CUDA_ERROR_NOT_MAPPED_AS_POINTERError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_ECC_UNCORRECTABLE
public static final int CUDA_ERROR_ECC_UNCORRECTABLEError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_UNSUPPORTED_LIMIT
public static final int CUDA_ERROR_UNSUPPORTED_LIMITError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_CONTEXT_ALREADY_IN_USE
public static final int CUDA_ERROR_CONTEXT_ALREADY_IN_USEError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_PEER_ACCESS_UNSUPPORTED
public static final int CUDA_ERROR_PEER_ACCESS_UNSUPPORTEDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_INVALID_PTX
public static final int CUDA_ERROR_INVALID_PTXError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_INVALID_GRAPHICS_CONTEXT
public static final int CUDA_ERROR_INVALID_GRAPHICS_CONTEXTError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_NVLINK_UNCORRECTABLE
public static final int CUDA_ERROR_NVLINK_UNCORRECTABLEError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_JIT_COMPILER_NOT_FOUND
public static final int CUDA_ERROR_JIT_COMPILER_NOT_FOUNDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_UNSUPPORTED_PTX_VERSION
public static final int CUDA_ERROR_UNSUPPORTED_PTX_VERSIONError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_JIT_COMPILATION_DISABLED
public static final int CUDA_ERROR_JIT_COMPILATION_DISABLEDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY
public static final int CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITYError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_INVALID_SOURCE
public static final int CUDA_ERROR_INVALID_SOURCEError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_FILE_NOT_FOUND
public static final int CUDA_ERROR_FILE_NOT_FOUNDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND
public static final int CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUNDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_SHARED_OBJECT_INIT_FAILED
public static final int CUDA_ERROR_SHARED_OBJECT_INIT_FAILEDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_OPERATING_SYSTEM
public static final int CUDA_ERROR_OPERATING_SYSTEMError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_INVALID_HANDLE
public static final int CUDA_ERROR_INVALID_HANDLEError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_ILLEGAL_STATE
public static final int CUDA_ERROR_ILLEGAL_STATEError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_NOT_FOUND
public static final int CUDA_ERROR_NOT_FOUNDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_NOT_READY
public static final int CUDA_ERROR_NOT_READYError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_ILLEGAL_ADDRESS
public static final int CUDA_ERROR_ILLEGAL_ADDRESSError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES
public static final int CUDA_ERROR_LAUNCH_OUT_OF_RESOURCESError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_LAUNCH_TIMEOUT
public static final int CUDA_ERROR_LAUNCH_TIMEOUTError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING
public static final int CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURINGError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED
public static final int CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLEDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_PEER_ACCESS_NOT_ENABLED
public static final int CUDA_ERROR_PEER_ACCESS_NOT_ENABLEDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE
public static final int CUDA_ERROR_PRIMARY_CONTEXT_ACTIVEError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_CONTEXT_IS_DESTROYED
public static final int CUDA_ERROR_CONTEXT_IS_DESTROYEDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_ASSERT
public static final int CUDA_ERROR_ASSERTError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_TOO_MANY_PEERS
public static final int CUDA_ERROR_TOO_MANY_PEERSError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED
public static final int CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTEREDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED
public static final int CUDA_ERROR_HOST_MEMORY_NOT_REGISTEREDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_HARDWARE_STACK_ERROR
public static final int CUDA_ERROR_HARDWARE_STACK_ERRORError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_ILLEGAL_INSTRUCTION
public static final int CUDA_ERROR_ILLEGAL_INSTRUCTIONError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_MISALIGNED_ADDRESS
public static final int CUDA_ERROR_MISALIGNED_ADDRESSError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_INVALID_ADDRESS_SPACE
public static final int CUDA_ERROR_INVALID_ADDRESS_SPACEError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_INVALID_PC
public static final int CUDA_ERROR_INVALID_PCError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_LAUNCH_FAILED
public static final int CUDA_ERROR_LAUNCH_FAILEDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE
public static final int CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGEError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_NOT_PERMITTED
public static final int CUDA_ERROR_NOT_PERMITTEDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_NOT_SUPPORTED
public static final int CUDA_ERROR_NOT_SUPPORTEDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_SYSTEM_NOT_READY
public static final int CUDA_ERROR_SYSTEM_NOT_READYError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_SYSTEM_DRIVER_MISMATCH
public static final int CUDA_ERROR_SYSTEM_DRIVER_MISMATCHError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE
public static final int CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICEError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_MPS_CONNECTION_FAILED
public static final int CUDA_ERROR_MPS_CONNECTION_FAILEDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_MPS_RPC_FAILURE
public static final int CUDA_ERROR_MPS_RPC_FAILUREError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_MPS_SERVER_NOT_READY
public static final int CUDA_ERROR_MPS_SERVER_NOT_READYError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_MPS_MAX_CLIENTS_REACHED
public static final int CUDA_ERROR_MPS_MAX_CLIENTS_REACHEDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED
public static final int CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHEDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED
public static final int CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTEDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_STREAM_CAPTURE_INVALIDATED
public static final int CUDA_ERROR_STREAM_CAPTURE_INVALIDATEDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_STREAM_CAPTURE_MERGE
public static final int CUDA_ERROR_STREAM_CAPTURE_MERGEError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_STREAM_CAPTURE_UNMATCHED
public static final int CUDA_ERROR_STREAM_CAPTURE_UNMATCHEDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_STREAM_CAPTURE_UNJOINED
public static final int CUDA_ERROR_STREAM_CAPTURE_UNJOINEDError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_STREAM_CAPTURE_ISOLATION
public static final int CUDA_ERROR_STREAM_CAPTURE_ISOLATIONError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_STREAM_CAPTURE_IMPLICIT
public static final int CUDA_ERROR_STREAM_CAPTURE_IMPLICITError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_CAPTURED_EVENT
public static final int CUDA_ERROR_CAPTURED_EVENTError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD
public static final int CUDA_ERROR_STREAM_CAPTURE_WRONG_THREADError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_TIMEOUT
public static final int CUDA_ERROR_TIMEOUTError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE
public static final int CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILUREError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_EXTERNAL_DEVICE
public static final int CUDA_ERROR_EXTERNAL_DEVICEError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CUDA_ERROR_UNKNOWN
public static final int CUDA_ERROR_UNKNOWNError codes. (CUresult)Enum values:
CUDA_SUCCESS- The API call returned with no errors.In the case of query calls, this also means that the operation being queried is complete (see
EventQueryandStreamQuery).CUDA_ERROR_INVALID_VALUE- This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.CUDA_ERROR_OUT_OF_MEMORY- The API call failed because it was unable to allocate enough memory to perform the requested operation.CUDA_ERROR_NOT_INITIALIZED- This indicates that the CUDA driver has not been initialized withInitor that initialization has failed.CUDA_ERROR_DEINITIALIZED- This indicates that the CUDA driver is in the process of shutting down.CUDA_ERROR_PROFILER_DISABLED- This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.CUDA_ERROR_PROFILER_NOT_INITIALIZED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling viaProfilerStartorProfilerStopwithout initialization.CUDA_ERROR_PROFILER_ALREADY_STARTED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStartwhen profiling is already enabled.CUDA_ERROR_PROFILER_ALREADY_STOPPED- Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to callProfilerStopwhen profiling is already disabled.CUDA_ERROR_STUB_LIBRARY- This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.CUDA_ERROR_NO_DEVICE- This indicates that no CUDA-capable devices were detected by the installed CUDA driver.CUDA_ERROR_INVALID_DEVICE- This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.CUDA_ERROR_DEVICE_NOT_LICENSED- This error indicates that the Grid license is not applied.CUDA_ERROR_INVALID_IMAGE- This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.CUDA_ERROR_INVALID_CONTEXT- This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has hadCtxDestroyinvoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). SeeCtxGetApiVersionfor more details.CUDA_ERROR_CONTEXT_ALREADY_CURRENT- This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context viaCtxPushCurrent.CUDA_ERROR_MAP_FAILED- This indicates that a map or register operation has failed.CUDA_ERROR_UNMAP_FAILED- This indicates that an unmap or unregister operation has failed.CUDA_ERROR_ARRAY_IS_MAPPED- This indicates that the specified array is currently mapped and thus cannot be destroyed.CUDA_ERROR_ALREADY_MAPPED- This indicates that the resource is already mapped.CUDA_ERROR_NO_BINARY_FOR_GPU- This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.CUDA_ERROR_ALREADY_ACQUIRED- This indicates that a resource has already been acquired.CUDA_ERROR_NOT_MAPPED- This indicates that a resource is not mapped.CUDA_ERROR_NOT_MAPPED_AS_ARRAY- This indicates that a mapped resource is not available for access as an array.CUDA_ERROR_NOT_MAPPED_AS_POINTER- This indicates that a mapped resource is not available for access as a pointer.CUDA_ERROR_ECC_UNCORRECTABLE- This indicates that an uncorrectable ECC error was detected during execution.CUDA_ERROR_UNSUPPORTED_LIMIT- This indicates that theCUlimitpassed to the API call is not supported by the active device.CUDA_ERROR_CONTEXT_ALREADY_IN_USE- This indicates that theCUcontextpassed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.CUDA_ERROR_PEER_ACCESS_UNSUPPORTED- This indicates that peer access is not supported across the given devices.CUDA_ERROR_INVALID_PTX- This indicates that a PTX JIT compilation failed.CUDA_ERROR_INVALID_GRAPHICS_CONTEXT- This indicates an error with OpenGL or DirectX context.CUDA_ERROR_NVLINK_UNCORRECTABLE- This indicates that an uncorrectable NVLink error was detected during the execution.CUDA_ERROR_JIT_COMPILER_NOT_FOUND- This indicates that the PTX JIT compiler library was not found.CUDA_ERROR_UNSUPPORTED_PTX_VERSION- This indicates that the provided PTX was compiled with an unsupported toolchain.CUDA_ERROR_JIT_COMPILATION_DISABLED- This indicates that the PTX JIT compilation was disabled.CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY- This indicates that theCUexecAffinityTypepassed to the API call is not supported by the active device.CUDA_ERROR_INVALID_SOURCE- This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.CUDA_ERROR_FILE_NOT_FOUND- This indicates that the file specified was not found.CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND- This indicates that a link to a shared object failed to resolve.CUDA_ERROR_SHARED_OBJECT_INIT_FAILED- This indicates that initialization of a shared object failed.CUDA_ERROR_OPERATING_SYSTEM- This indicates that an OS call failed.CUDA_ERROR_INVALID_HANDLE- This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types likeCUstreamandCUevent.CUDA_ERROR_ILLEGAL_STATE- This indicates that a resource required by the API call is not in a valid state to perform the requested operation.CUDA_ERROR_NOT_FOUND- This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.CUDA_ERROR_NOT_READY- This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently thanCUDA_SUCCESS(which indicates completion). Calls that may return this value includeEventQueryandStreamQuery.CUDA_ERROR_ILLEGAL_ADDRESS- While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES- This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.CUDA_ERROR_LAUNCH_TIMEOUT- This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attributeDEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUTfor more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING- This error indicates a kernel launch that uses an incompatible texturing mode.CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED- This error indicates that a call toCtxEnablePeerAccessis trying to re-enable peer access to a context which has already had peer access to it enabled.CUDA_ERROR_PEER_ACCESS_NOT_ENABLED- This error indicates thatCtxDisablePeerAccessis trying to disable peer access which has not been enabled yet viaCtxEnablePeerAccess.CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE- This error indicates that the primary context for the specified device has already been initialized.CUDA_ERROR_CONTEXT_IS_DESTROYED- This error indicates that the context current to the calling thread has been destroyed usingCtxDestroy, or is a primary context which has not yet been initialized.CUDA_ERROR_ASSERT- A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.CUDA_ERROR_TOO_MANY_PEERS- This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed toCtxEnablePeerAccess.CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED- This error indicates that the memory range passed toMemHostRegisterhas already been registered.CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED- This error indicates that the pointer passed toMemHostUnregisterdoes not correspond to any currently registered memory region.CUDA_ERROR_HARDWARE_STACK_ERROR- While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_ILLEGAL_INSTRUCTION- While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_MISALIGNED_ADDRESS- While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_ADDRESS_SPACE- While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_INVALID_PC- While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_LAUNCH_FAILED- An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE- This error indicates that the number of blocks launched per grid for a kernel that was launched via eitherLaunchCooperativeKernelorLaunchCooperativeKernelMultiDeviceexceeds the maximum number of blocks as allowed byOccupancyMaxActiveBlocksPerMultiprocessororOccupancyMaxActiveBlocksPerMultiprocessorWithFlagstimes the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.CUDA_ERROR_NOT_PERMITTED- This error indicates that the attempted operation is not permitted.CUDA_ERROR_NOT_SUPPORTED- This error indicates that the attempted operation is not supported on the current system or device.CUDA_ERROR_SYSTEM_NOT_READY- This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.CUDA_ERROR_SYSTEM_DRIVER_MISMATCH- This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE- This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via theCUDA_VISIBLE_DEVICESenvironment variable.CUDA_ERROR_MPS_CONNECTION_FAILED- This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.CUDA_ERROR_MPS_RPC_FAILURE- This error indicates that the remote procedural call between the MPS server and the MPS client failed.CUDA_ERROR_MPS_SERVER_NOT_READY- This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.CUDA_ERROR_MPS_MAX_CLIENTS_REACHED- This error indicates that the hardware resources required to create MPS client have been exhausted.CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED- This error indicates the the hardware resources required to support device connections have been exhausted.CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED- This error indicates that the operation is not permitted when the stream is capturing.CUDA_ERROR_STREAM_CAPTURE_INVALIDATED- This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.CUDA_ERROR_STREAM_CAPTURE_MERGE- This error indicates that the operation would have resulted in a merge of two independent capture sequences.CUDA_ERROR_STREAM_CAPTURE_UNMATCHED- This error indicates that the capture was not initiated in this stream.CUDA_ERROR_STREAM_CAPTURE_UNJOINED- This error indicates that the capture sequence contains a fork that was not joined to the primary stream.CUDA_ERROR_STREAM_CAPTURE_ISOLATION- This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT- This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.CUDA_ERROR_CAPTURED_EVENT- This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD- A stream capture sequence not initiated with theSTREAM_CAPTURE_MODE_RELAXEDargument toStreamBeginCapturewas passed toStreamEndCapturein a different thread.CUDA_ERROR_TIMEOUT- This error indicates that the timeout specified for the wait operation has lapsed.CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE- This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.CUDA_ERROR_EXTERNAL_DEVICE- This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.CUDA_ERROR_UNKNOWN- This indicates that an unknown internal error has occurred.
- See Also:
-
CU_DEVICE_P2P_ATTRIBUTE_PERFORMANCE_RANK
public static final int CU_DEVICE_P2P_ATTRIBUTE_PERFORMANCE_RANKP2P Attributes. (CUdevice_P2PAttribute)Enum values:
DEVICE_P2P_ATTRIBUTE_PERFORMANCE_RANK- A relative value indicating the performance of the link between two devicesDEVICE_P2P_ATTRIBUTE_ACCESS_SUPPORTED- P2P Access is enableDEVICE_P2P_ATTRIBUTE_NATIVE_ATOMIC_SUPPORTED- Atomic operation over the link supportedDEVICE_P2P_ATTRIBUTE_ACCESS_ACCESS_SUPPORTED- Deprecated, use CU_DEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTED insteadDEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTED- Accessing CUDA arrays over the link supported
- See Also:
-
CU_DEVICE_P2P_ATTRIBUTE_ACCESS_SUPPORTED
public static final int CU_DEVICE_P2P_ATTRIBUTE_ACCESS_SUPPORTEDP2P Attributes. (CUdevice_P2PAttribute)Enum values:
DEVICE_P2P_ATTRIBUTE_PERFORMANCE_RANK- A relative value indicating the performance of the link between two devicesDEVICE_P2P_ATTRIBUTE_ACCESS_SUPPORTED- P2P Access is enableDEVICE_P2P_ATTRIBUTE_NATIVE_ATOMIC_SUPPORTED- Atomic operation over the link supportedDEVICE_P2P_ATTRIBUTE_ACCESS_ACCESS_SUPPORTED- Deprecated, use CU_DEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTED insteadDEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTED- Accessing CUDA arrays over the link supported
- See Also:
-
CU_DEVICE_P2P_ATTRIBUTE_NATIVE_ATOMIC_SUPPORTED
public static final int CU_DEVICE_P2P_ATTRIBUTE_NATIVE_ATOMIC_SUPPORTEDP2P Attributes. (CUdevice_P2PAttribute)Enum values:
DEVICE_P2P_ATTRIBUTE_PERFORMANCE_RANK- A relative value indicating the performance of the link between two devicesDEVICE_P2P_ATTRIBUTE_ACCESS_SUPPORTED- P2P Access is enableDEVICE_P2P_ATTRIBUTE_NATIVE_ATOMIC_SUPPORTED- Atomic operation over the link supportedDEVICE_P2P_ATTRIBUTE_ACCESS_ACCESS_SUPPORTED- Deprecated, use CU_DEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTED insteadDEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTED- Accessing CUDA arrays over the link supported
- See Also:
-
CU_DEVICE_P2P_ATTRIBUTE_ACCESS_ACCESS_SUPPORTED
public static final int CU_DEVICE_P2P_ATTRIBUTE_ACCESS_ACCESS_SUPPORTEDP2P Attributes. (CUdevice_P2PAttribute)Enum values:
DEVICE_P2P_ATTRIBUTE_PERFORMANCE_RANK- A relative value indicating the performance of the link between two devicesDEVICE_P2P_ATTRIBUTE_ACCESS_SUPPORTED- P2P Access is enableDEVICE_P2P_ATTRIBUTE_NATIVE_ATOMIC_SUPPORTED- Atomic operation over the link supportedDEVICE_P2P_ATTRIBUTE_ACCESS_ACCESS_SUPPORTED- Deprecated, use CU_DEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTED insteadDEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTED- Accessing CUDA arrays over the link supported
- See Also:
-
CU_DEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTED
public static final int CU_DEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTEDP2P Attributes. (CUdevice_P2PAttribute)Enum values:
DEVICE_P2P_ATTRIBUTE_PERFORMANCE_RANK- A relative value indicating the performance of the link between two devicesDEVICE_P2P_ATTRIBUTE_ACCESS_SUPPORTED- P2P Access is enableDEVICE_P2P_ATTRIBUTE_NATIVE_ATOMIC_SUPPORTED- Atomic operation over the link supportedDEVICE_P2P_ATTRIBUTE_ACCESS_ACCESS_SUPPORTED- Deprecated, use CU_DEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTED insteadDEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTED- Accessing CUDA arrays over the link supported
- See Also:
-
CU_MEMHOSTALLOC_PORTABLE
public static final int CU_MEMHOSTALLOC_PORTABLEFlags forMemHostAlloc.Enum values:
MEMHOSTALLOC_PORTABLE- If set, host memory is portable between CUDA contexts.MEMHOSTALLOC_DEVICEMAP- If set, host memory is mapped into CUDA address space andMemHostGetDevicePointermay be called on the host pointer.MEMHOSTALLOC_WRITECOMBINED- If set, host memory is allocated as write-combined - fast to write, faster to DMA, slow to read except via SSE4 streaming load instruction (MOVNTDQA).
- See Also:
-
CU_MEMHOSTALLOC_DEVICEMAP
public static final int CU_MEMHOSTALLOC_DEVICEMAPFlags forMemHostAlloc.Enum values:
MEMHOSTALLOC_PORTABLE- If set, host memory is portable between CUDA contexts.MEMHOSTALLOC_DEVICEMAP- If set, host memory is mapped into CUDA address space andMemHostGetDevicePointermay be called on the host pointer.MEMHOSTALLOC_WRITECOMBINED- If set, host memory is allocated as write-combined - fast to write, faster to DMA, slow to read except via SSE4 streaming load instruction (MOVNTDQA).
- See Also:
-
CU_MEMHOSTALLOC_WRITECOMBINED
public static final int CU_MEMHOSTALLOC_WRITECOMBINEDFlags forMemHostAlloc.Enum values:
MEMHOSTALLOC_PORTABLE- If set, host memory is portable between CUDA contexts.MEMHOSTALLOC_DEVICEMAP- If set, host memory is mapped into CUDA address space andMemHostGetDevicePointermay be called on the host pointer.MEMHOSTALLOC_WRITECOMBINED- If set, host memory is allocated as write-combined - fast to write, faster to DMA, slow to read except via SSE4 streaming load instruction (MOVNTDQA).
- See Also:
-
CU_MEMHOSTREGISTER_PORTABLE
public static final int CU_MEMHOSTREGISTER_PORTABLEFlags forMemHostRegister.Enum values:
MEMHOSTREGISTER_PORTABLE- If set, host memory is portable between CUDA contexts.MEMHOSTREGISTER_DEVICEMAP- If set, host memory is mapped into CUDA address space andMemHostGetDevicePointermay be called on the host pointer.MEMHOSTREGISTER_IOMEMORY- If set, the passed memory pointer is treated as pointing to some memory-mapped I/O space, e.g. belonging to a third-party PCIe device.On Windows the flag is a no-op. On Linux that memory is marked as non cache-coherent for the GPU and is expected to be physically contiguous. It may return
CUDA_ERROR_NOT_PERMITTEDif run as an unprivileged user,CUDA_ERROR_NOT_SUPPORTEDon older Linux kernel versions. On all other platforms, it is not supported andCUDA_ERROR_NOT_SUPPORTEDis returned.MEMHOSTREGISTER_READ_ONLY- If set, the passed memory pointer is treated as pointing to memory that is considered read-only by the device.On platforms without
DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES, this flag is required in order to register memory mapped to the CPU as read-only. Support for the use of this flag can be queried from the device attributeDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED. Using this flag with a current context associated with a device that does not have this attribute set will causeMemHostRegisterto error withCUDA_ERROR_NOT_SUPPORTED.
- See Also:
-
CU_MEMHOSTREGISTER_DEVICEMAP
public static final int CU_MEMHOSTREGISTER_DEVICEMAPFlags forMemHostRegister.Enum values:
MEMHOSTREGISTER_PORTABLE- If set, host memory is portable between CUDA contexts.MEMHOSTREGISTER_DEVICEMAP- If set, host memory is mapped into CUDA address space andMemHostGetDevicePointermay be called on the host pointer.MEMHOSTREGISTER_IOMEMORY- If set, the passed memory pointer is treated as pointing to some memory-mapped I/O space, e.g. belonging to a third-party PCIe device.On Windows the flag is a no-op. On Linux that memory is marked as non cache-coherent for the GPU and is expected to be physically contiguous. It may return
CUDA_ERROR_NOT_PERMITTEDif run as an unprivileged user,CUDA_ERROR_NOT_SUPPORTEDon older Linux kernel versions. On all other platforms, it is not supported andCUDA_ERROR_NOT_SUPPORTEDis returned.MEMHOSTREGISTER_READ_ONLY- If set, the passed memory pointer is treated as pointing to memory that is considered read-only by the device.On platforms without
DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES, this flag is required in order to register memory mapped to the CPU as read-only. Support for the use of this flag can be queried from the device attributeDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED. Using this flag with a current context associated with a device that does not have this attribute set will causeMemHostRegisterto error withCUDA_ERROR_NOT_SUPPORTED.
- See Also:
-
CU_MEMHOSTREGISTER_IOMEMORY
public static final int CU_MEMHOSTREGISTER_IOMEMORYFlags forMemHostRegister.Enum values:
MEMHOSTREGISTER_PORTABLE- If set, host memory is portable between CUDA contexts.MEMHOSTREGISTER_DEVICEMAP- If set, host memory is mapped into CUDA address space andMemHostGetDevicePointermay be called on the host pointer.MEMHOSTREGISTER_IOMEMORY- If set, the passed memory pointer is treated as pointing to some memory-mapped I/O space, e.g. belonging to a third-party PCIe device.On Windows the flag is a no-op. On Linux that memory is marked as non cache-coherent for the GPU and is expected to be physically contiguous. It may return
CUDA_ERROR_NOT_PERMITTEDif run as an unprivileged user,CUDA_ERROR_NOT_SUPPORTEDon older Linux kernel versions. On all other platforms, it is not supported andCUDA_ERROR_NOT_SUPPORTEDis returned.MEMHOSTREGISTER_READ_ONLY- If set, the passed memory pointer is treated as pointing to memory that is considered read-only by the device.On platforms without
DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES, this flag is required in order to register memory mapped to the CPU as read-only. Support for the use of this flag can be queried from the device attributeDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED. Using this flag with a current context associated with a device that does not have this attribute set will causeMemHostRegisterto error withCUDA_ERROR_NOT_SUPPORTED.
- See Also:
-
CU_MEMHOSTREGISTER_READ_ONLY
public static final int CU_MEMHOSTREGISTER_READ_ONLYFlags forMemHostRegister.Enum values:
MEMHOSTREGISTER_PORTABLE- If set, host memory is portable between CUDA contexts.MEMHOSTREGISTER_DEVICEMAP- If set, host memory is mapped into CUDA address space andMemHostGetDevicePointermay be called on the host pointer.MEMHOSTREGISTER_IOMEMORY- If set, the passed memory pointer is treated as pointing to some memory-mapped I/O space, e.g. belonging to a third-party PCIe device.On Windows the flag is a no-op. On Linux that memory is marked as non cache-coherent for the GPU and is expected to be physically contiguous. It may return
CUDA_ERROR_NOT_PERMITTEDif run as an unprivileged user,CUDA_ERROR_NOT_SUPPORTEDon older Linux kernel versions. On all other platforms, it is not supported andCUDA_ERROR_NOT_SUPPORTEDis returned.MEMHOSTREGISTER_READ_ONLY- If set, the passed memory pointer is treated as pointing to memory that is considered read-only by the device.On platforms without
DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES, this flag is required in order to register memory mapped to the CPU as read-only. Support for the use of this flag can be queried from the device attributeDEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED. Using this flag with a current context associated with a device that does not have this attribute set will causeMemHostRegisterto error withCUDA_ERROR_NOT_SUPPORTED.
- See Also:
-
CU_ARRAY_SPARSE_PROPERTIES_SINGLE_MIPTAIL
public static final int CU_ARRAY_SPARSE_PROPERTIES_SINGLE_MIPTAILIndicates that the layered sparse CUDA array or CUDA mipmapped array has a single mip tail region for all layers.- See Also:
-
CU_RES_VIEW_FORMAT_NONE
public static final int CU_RES_VIEW_FORMAT_NONEResource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_UINT_1X8
public static final int CU_RES_VIEW_FORMAT_UINT_1X8Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_UINT_2X8
public static final int CU_RES_VIEW_FORMAT_UINT_2X8Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_UINT_4X8
public static final int CU_RES_VIEW_FORMAT_UINT_4X8Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_SINT_1X8
public static final int CU_RES_VIEW_FORMAT_SINT_1X8Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_SINT_2X8
public static final int CU_RES_VIEW_FORMAT_SINT_2X8Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_SINT_4X8
public static final int CU_RES_VIEW_FORMAT_SINT_4X8Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_UINT_1X16
public static final int CU_RES_VIEW_FORMAT_UINT_1X16Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_UINT_2X16
public static final int CU_RES_VIEW_FORMAT_UINT_2X16Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_UINT_4X16
public static final int CU_RES_VIEW_FORMAT_UINT_4X16Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_SINT_1X16
public static final int CU_RES_VIEW_FORMAT_SINT_1X16Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_SINT_2X16
public static final int CU_RES_VIEW_FORMAT_SINT_2X16Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_SINT_4X16
public static final int CU_RES_VIEW_FORMAT_SINT_4X16Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_UINT_1X32
public static final int CU_RES_VIEW_FORMAT_UINT_1X32Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_UINT_2X32
public static final int CU_RES_VIEW_FORMAT_UINT_2X32Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_UINT_4X32
public static final int CU_RES_VIEW_FORMAT_UINT_4X32Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_SINT_1X32
public static final int CU_RES_VIEW_FORMAT_SINT_1X32Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_SINT_2X32
public static final int CU_RES_VIEW_FORMAT_SINT_2X32Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_SINT_4X32
public static final int CU_RES_VIEW_FORMAT_SINT_4X32Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_FLOAT_1X16
public static final int CU_RES_VIEW_FORMAT_FLOAT_1X16Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_FLOAT_2X16
public static final int CU_RES_VIEW_FORMAT_FLOAT_2X16Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_FLOAT_4X16
public static final int CU_RES_VIEW_FORMAT_FLOAT_4X16Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_FLOAT_1X32
public static final int CU_RES_VIEW_FORMAT_FLOAT_1X32Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_FLOAT_2X32
public static final int CU_RES_VIEW_FORMAT_FLOAT_2X32Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_FLOAT_4X32
public static final int CU_RES_VIEW_FORMAT_FLOAT_4X32Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_UNSIGNED_BC1
public static final int CU_RES_VIEW_FORMAT_UNSIGNED_BC1Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_UNSIGNED_BC2
public static final int CU_RES_VIEW_FORMAT_UNSIGNED_BC2Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_UNSIGNED_BC3
public static final int CU_RES_VIEW_FORMAT_UNSIGNED_BC3Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_UNSIGNED_BC4
public static final int CU_RES_VIEW_FORMAT_UNSIGNED_BC4Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_SIGNED_BC4
public static final int CU_RES_VIEW_FORMAT_SIGNED_BC4Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_UNSIGNED_BC5
public static final int CU_RES_VIEW_FORMAT_UNSIGNED_BC5Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_SIGNED_BC5
public static final int CU_RES_VIEW_FORMAT_SIGNED_BC5Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_UNSIGNED_BC6H
public static final int CU_RES_VIEW_FORMAT_UNSIGNED_BC6HResource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_SIGNED_BC6H
public static final int CU_RES_VIEW_FORMAT_SIGNED_BC6HResource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_RES_VIEW_FORMAT_UNSIGNED_BC7
public static final int CU_RES_VIEW_FORMAT_UNSIGNED_BC7Resource view format. (CUresourceViewFormat)Enum values:
RES_VIEW_FORMAT_NONE- No resource view format (use underlying resource format)RES_VIEW_FORMAT_UINT_1X8- 1 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_2X8- 2 channel unsigned 8-bit integersRES_VIEW_FORMAT_UINT_4X8- 4 channel unsigned 8-bit integersRES_VIEW_FORMAT_SINT_1X8- 1 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_2X8- 2 channel signed 8-bit integersRES_VIEW_FORMAT_SINT_4X8- 4 channel signed 8-bit integersRES_VIEW_FORMAT_UINT_1X16- 1 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_2X16- 2 channel unsigned 16-bit integersRES_VIEW_FORMAT_UINT_4X16- 4 channel unsigned 16-bit integersRES_VIEW_FORMAT_SINT_1X16- 1 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_2X16- 2 channel signed 16-bit integersRES_VIEW_FORMAT_SINT_4X16- 4 channel signed 16-bit integersRES_VIEW_FORMAT_UINT_1X32- 1 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_2X32- 2 channel unsigned 32-bit integersRES_VIEW_FORMAT_UINT_4X32- 4 channel unsigned 32-bit integersRES_VIEW_FORMAT_SINT_1X32- 1 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_2X32- 2 channel signed 32-bit integersRES_VIEW_FORMAT_SINT_4X32- 4 channel signed 32-bit integersRES_VIEW_FORMAT_FLOAT_1X16- 1 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_2X16- 2 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_4X16- 4 channel 16-bit floating pointRES_VIEW_FORMAT_FLOAT_1X32- 1 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_2X32- 2 channel 32-bit floating pointRES_VIEW_FORMAT_FLOAT_4X32- 4 channel 32-bit floating pointRES_VIEW_FORMAT_UNSIGNED_BC1- Block compressed 1RES_VIEW_FORMAT_UNSIGNED_BC2- Block compressed 2RES_VIEW_FORMAT_UNSIGNED_BC3- Block compressed 3RES_VIEW_FORMAT_UNSIGNED_BC4- Block compressed 4 unsignedRES_VIEW_FORMAT_SIGNED_BC4- Block compressed 4 signedRES_VIEW_FORMAT_UNSIGNED_BC5- Block compressed 5 unsignedRES_VIEW_FORMAT_SIGNED_BC5- Block compressed 5 signedRES_VIEW_FORMAT_UNSIGNED_BC6H- Block compressed 6 unsigned half-floatRES_VIEW_FORMAT_SIGNED_BC6H- Block compressed 6 signed half-floatRES_VIEW_FORMAT_UNSIGNED_BC7- Block compressed 7
- See Also:
-
CU_POINTER_ATTRIBUTE_ACCESS_FLAG_NONE
public static final int CU_POINTER_ATTRIBUTE_ACCESS_FLAG_NONEAccess flags that specify the level of access the current context's device has on the memory referenced. (CUDA_POINTER_ATTRIBUTE_ACCESS_FLAGS)Enum values:
POINTER_ATTRIBUTE_ACCESS_FLAG_NONE- No access, meaning the device cannot access this memory at all, thus must be staged through accessible memory in order to complete certain operationsPOINTER_ATTRIBUTE_ACCESS_FLAG_READ- Read-only access, meaning writes to this memory are considered invalid accesses and thus return error in that case.POINTER_ATTRIBUTE_ACCESS_FLAG_READWRITE- Read-write access, the device has full read-write access to the memory
- See Also:
-
CU_POINTER_ATTRIBUTE_ACCESS_FLAG_READ
public static final int CU_POINTER_ATTRIBUTE_ACCESS_FLAG_READAccess flags that specify the level of access the current context's device has on the memory referenced. (CUDA_POINTER_ATTRIBUTE_ACCESS_FLAGS)Enum values:
POINTER_ATTRIBUTE_ACCESS_FLAG_NONE- No access, meaning the device cannot access this memory at all, thus must be staged through accessible memory in order to complete certain operationsPOINTER_ATTRIBUTE_ACCESS_FLAG_READ- Read-only access, meaning writes to this memory are considered invalid accesses and thus return error in that case.POINTER_ATTRIBUTE_ACCESS_FLAG_READWRITE- Read-write access, the device has full read-write access to the memory
- See Also:
-
CU_POINTER_ATTRIBUTE_ACCESS_FLAG_READWRITE
public static final int CU_POINTER_ATTRIBUTE_ACCESS_FLAG_READWRITEAccess flags that specify the level of access the current context's device has on the memory referenced. (CUDA_POINTER_ATTRIBUTE_ACCESS_FLAGS)Enum values:
POINTER_ATTRIBUTE_ACCESS_FLAG_NONE- No access, meaning the device cannot access this memory at all, thus must be staged through accessible memory in order to complete certain operationsPOINTER_ATTRIBUTE_ACCESS_FLAG_READ- Read-only access, meaning writes to this memory are considered invalid accesses and thus return error in that case.POINTER_ATTRIBUTE_ACCESS_FLAG_READWRITE- Read-write access, the device has full read-write access to the memory
- See Also:
-
CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FD
public static final int CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FDExternal memory handle types. (CUexternalMemoryHandleType)Enum values:
EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FD- Handle is an opaque file descriptorEXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32- Handle is an opaque shared NT handleEXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_KMT- Handle is an opaque, globally shared handleEXTERNAL_MEMORY_HANDLE_TYPE_D3D12_HEAP- Handle is a D3D12 heap objectEXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE- Handle is a D3D12 committed resourceEXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE- Handle is a shared NT handle to a D3D11 resourceEXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT- Handle is a globally shared handle to a D3D11 resourceEXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF- Handle is an NvSciBuf object
- See Also:
-
CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32
public static final int CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32External memory handle types. (CUexternalMemoryHandleType)Enum values:
EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FD- Handle is an opaque file descriptorEXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32- Handle is an opaque shared NT handleEXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_KMT- Handle is an opaque, globally shared handleEXTERNAL_MEMORY_HANDLE_TYPE_D3D12_HEAP- Handle is a D3D12 heap objectEXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE- Handle is a D3D12 committed resourceEXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE- Handle is a shared NT handle to a D3D11 resourceEXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT- Handle is a globally shared handle to a D3D11 resourceEXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF- Handle is an NvSciBuf object
- See Also:
-
CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_KMT
public static final int CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_KMTExternal memory handle types. (CUexternalMemoryHandleType)Enum values:
EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FD- Handle is an opaque file descriptorEXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32- Handle is an opaque shared NT handleEXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_KMT- Handle is an opaque, globally shared handleEXTERNAL_MEMORY_HANDLE_TYPE_D3D12_HEAP- Handle is a D3D12 heap objectEXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE- Handle is a D3D12 committed resourceEXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE- Handle is a shared NT handle to a D3D11 resourceEXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT- Handle is a globally shared handle to a D3D11 resourceEXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF- Handle is an NvSciBuf object
- See Also:
-
CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_HEAP
public static final int CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_HEAPExternal memory handle types. (CUexternalMemoryHandleType)Enum values:
EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FD- Handle is an opaque file descriptorEXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32- Handle is an opaque shared NT handleEXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_KMT- Handle is an opaque, globally shared handleEXTERNAL_MEMORY_HANDLE_TYPE_D3D12_HEAP- Handle is a D3D12 heap objectEXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE- Handle is a D3D12 committed resourceEXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE- Handle is a shared NT handle to a D3D11 resourceEXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT- Handle is a globally shared handle to a D3D11 resourceEXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF- Handle is an NvSciBuf object
- See Also:
-
CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE
public static final int CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCEExternal memory handle types. (CUexternalMemoryHandleType)Enum values:
EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FD- Handle is an opaque file descriptorEXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32- Handle is an opaque shared NT handleEXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_KMT- Handle is an opaque, globally shared handleEXTERNAL_MEMORY_HANDLE_TYPE_D3D12_HEAP- Handle is a D3D12 heap objectEXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE- Handle is a D3D12 committed resourceEXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE- Handle is a shared NT handle to a D3D11 resourceEXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT- Handle is a globally shared handle to a D3D11 resourceEXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF- Handle is an NvSciBuf object
- See Also:
-
CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE
public static final int CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCEExternal memory handle types. (CUexternalMemoryHandleType)Enum values:
EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FD- Handle is an opaque file descriptorEXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32- Handle is an opaque shared NT handleEXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_KMT- Handle is an opaque, globally shared handleEXTERNAL_MEMORY_HANDLE_TYPE_D3D12_HEAP- Handle is a D3D12 heap objectEXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE- Handle is a D3D12 committed resourceEXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE- Handle is a shared NT handle to a D3D11 resourceEXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT- Handle is a globally shared handle to a D3D11 resourceEXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF- Handle is an NvSciBuf object
- See Also:
-
CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT
public static final int CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMTExternal memory handle types. (CUexternalMemoryHandleType)Enum values:
EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FD- Handle is an opaque file descriptorEXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32- Handle is an opaque shared NT handleEXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_KMT- Handle is an opaque, globally shared handleEXTERNAL_MEMORY_HANDLE_TYPE_D3D12_HEAP- Handle is a D3D12 heap objectEXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE- Handle is a D3D12 committed resourceEXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE- Handle is a shared NT handle to a D3D11 resourceEXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT- Handle is a globally shared handle to a D3D11 resourceEXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF- Handle is an NvSciBuf object
- See Also:
-
CU_EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF
public static final int CU_EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUFExternal memory handle types. (CUexternalMemoryHandleType)Enum values:
EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FD- Handle is an opaque file descriptorEXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32- Handle is an opaque shared NT handleEXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_KMT- Handle is an opaque, globally shared handleEXTERNAL_MEMORY_HANDLE_TYPE_D3D12_HEAP- Handle is a D3D12 heap objectEXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE- Handle is a D3D12 committed resourceEXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE- Handle is a shared NT handle to a D3D11 resourceEXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT- Handle is a globally shared handle to a D3D11 resourceEXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF- Handle is an NvSciBuf object
- See Also:
-
CUDA_EXTERNAL_MEMORY_DEDICATED
public static final int CUDA_EXTERNAL_MEMORY_DEDICATEDIndicates that the external memory object is a dedicated resource.- See Also:
-
CUDA_EXTERNAL_SEMAPHORE_SIGNAL_SKIP_NVSCIBUF_MEMSYNC
public static final int CUDA_EXTERNAL_SEMAPHORE_SIGNAL_SKIP_NVSCIBUF_MEMSYNCWhen theflagsparameter ofCUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMScontains this flag, it indicates that signaling an external semaphore object should skip performing appropriate memory synchronization operations over all the external memory objects that are imported asEXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF, which otherwise are performed by default to ensure data coherency with other importers of the sameNvSciBufmemory objects.- See Also:
-
CUDA_EXTERNAL_SEMAPHORE_WAIT_SKIP_NVSCIBUF_MEMSYNC
public static final int CUDA_EXTERNAL_SEMAPHORE_WAIT_SKIP_NVSCIBUF_MEMSYNCWhen theflagsparameter ofCUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMScontains this flag, it indicates that waiting on an external semaphore object should skip performing appropriate memory synchronization operations over all the external memory objects that are imported asEXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF, which otherwise are performed by default to ensure data coherency with other importers of the sameNvSciBufmemory objects.- See Also:
-
CUDA_NVSCISYNC_ATTR_SIGNAL
public static final int CUDA_NVSCISYNC_ATTR_SIGNALWhenflagsofDeviceGetNvSciSyncAttributesis set to this, it indicates that application needs signaler specificNvSciSyncAttrto be filled bycuDeviceGetNvSciSyncAttributes.- See Also:
-
CUDA_NVSCISYNC_ATTR_WAIT
public static final int CUDA_NVSCISYNC_ATTR_WAITWhenflagsofDeviceGetNvSciSyncAttributesis set to this, it indicates that application needs waiter specificNvSciSyncAttrto be filled bycuDeviceGetNvSciSyncAttributes.- See Also:
-
CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD
public static final int CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FDExternal semaphore handle types. (CUexternalSemaphoreHandleType)Enum values:
EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD- Handle is an opaque file descriptorEXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32- Handle is an opaque shared NT handleEXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT- Handle is an opaque, globally shared handleEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE- Handle is a shared NT handle referencing a D3D12 fence objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE- Handle is a shared NT handle referencing a D3D11 fence objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC- Opaque handle to NvSciSync ObjectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX- Handle is a shared NT handle referencing a D3D11 keyed mutex objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT- Handle is a globally shared handle referencing a D3D11 keyed mutex objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD- Handle is an opaque file descriptor referencing a timeline semaphoreEXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32- Handle is an opaque shared NT handle referencing a timeline semaphore
- See Also:
-
CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32
public static final int CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32External semaphore handle types. (CUexternalSemaphoreHandleType)Enum values:
EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD- Handle is an opaque file descriptorEXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32- Handle is an opaque shared NT handleEXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT- Handle is an opaque, globally shared handleEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE- Handle is a shared NT handle referencing a D3D12 fence objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE- Handle is a shared NT handle referencing a D3D11 fence objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC- Opaque handle to NvSciSync ObjectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX- Handle is a shared NT handle referencing a D3D11 keyed mutex objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT- Handle is a globally shared handle referencing a D3D11 keyed mutex objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD- Handle is an opaque file descriptor referencing a timeline semaphoreEXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32- Handle is an opaque shared NT handle referencing a timeline semaphore
- See Also:
-
CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT
public static final int CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMTExternal semaphore handle types. (CUexternalSemaphoreHandleType)Enum values:
EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD- Handle is an opaque file descriptorEXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32- Handle is an opaque shared NT handleEXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT- Handle is an opaque, globally shared handleEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE- Handle is a shared NT handle referencing a D3D12 fence objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE- Handle is a shared NT handle referencing a D3D11 fence objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC- Opaque handle to NvSciSync ObjectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX- Handle is a shared NT handle referencing a D3D11 keyed mutex objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT- Handle is a globally shared handle referencing a D3D11 keyed mutex objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD- Handle is an opaque file descriptor referencing a timeline semaphoreEXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32- Handle is an opaque shared NT handle referencing a timeline semaphore
- See Also:
-
CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE
public static final int CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCEExternal semaphore handle types. (CUexternalSemaphoreHandleType)Enum values:
EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD- Handle is an opaque file descriptorEXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32- Handle is an opaque shared NT handleEXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT- Handle is an opaque, globally shared handleEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE- Handle is a shared NT handle referencing a D3D12 fence objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE- Handle is a shared NT handle referencing a D3D11 fence objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC- Opaque handle to NvSciSync ObjectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX- Handle is a shared NT handle referencing a D3D11 keyed mutex objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT- Handle is a globally shared handle referencing a D3D11 keyed mutex objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD- Handle is an opaque file descriptor referencing a timeline semaphoreEXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32- Handle is an opaque shared NT handle referencing a timeline semaphore
- See Also:
-
CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE
public static final int CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCEExternal semaphore handle types. (CUexternalSemaphoreHandleType)Enum values:
EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD- Handle is an opaque file descriptorEXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32- Handle is an opaque shared NT handleEXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT- Handle is an opaque, globally shared handleEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE- Handle is a shared NT handle referencing a D3D12 fence objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE- Handle is a shared NT handle referencing a D3D11 fence objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC- Opaque handle to NvSciSync ObjectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX- Handle is a shared NT handle referencing a D3D11 keyed mutex objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT- Handle is a globally shared handle referencing a D3D11 keyed mutex objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD- Handle is an opaque file descriptor referencing a timeline semaphoreEXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32- Handle is an opaque shared NT handle referencing a timeline semaphore
- See Also:
-
CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC
public static final int CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNCExternal semaphore handle types. (CUexternalSemaphoreHandleType)Enum values:
EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD- Handle is an opaque file descriptorEXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32- Handle is an opaque shared NT handleEXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT- Handle is an opaque, globally shared handleEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE- Handle is a shared NT handle referencing a D3D12 fence objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE- Handle is a shared NT handle referencing a D3D11 fence objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC- Opaque handle to NvSciSync ObjectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX- Handle is a shared NT handle referencing a D3D11 keyed mutex objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT- Handle is a globally shared handle referencing a D3D11 keyed mutex objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD- Handle is an opaque file descriptor referencing a timeline semaphoreEXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32- Handle is an opaque shared NT handle referencing a timeline semaphore
- See Also:
-
CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX
public static final int CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEXExternal semaphore handle types. (CUexternalSemaphoreHandleType)Enum values:
EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD- Handle is an opaque file descriptorEXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32- Handle is an opaque shared NT handleEXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT- Handle is an opaque, globally shared handleEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE- Handle is a shared NT handle referencing a D3D12 fence objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE- Handle is a shared NT handle referencing a D3D11 fence objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC- Opaque handle to NvSciSync ObjectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX- Handle is a shared NT handle referencing a D3D11 keyed mutex objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT- Handle is a globally shared handle referencing a D3D11 keyed mutex objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD- Handle is an opaque file descriptor referencing a timeline semaphoreEXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32- Handle is an opaque shared NT handle referencing a timeline semaphore
- See Also:
-
CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT
public static final int CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMTExternal semaphore handle types. (CUexternalSemaphoreHandleType)Enum values:
EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD- Handle is an opaque file descriptorEXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32- Handle is an opaque shared NT handleEXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT- Handle is an opaque, globally shared handleEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE- Handle is a shared NT handle referencing a D3D12 fence objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE- Handle is a shared NT handle referencing a D3D11 fence objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC- Opaque handle to NvSciSync ObjectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX- Handle is a shared NT handle referencing a D3D11 keyed mutex objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT- Handle is a globally shared handle referencing a D3D11 keyed mutex objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD- Handle is an opaque file descriptor referencing a timeline semaphoreEXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32- Handle is an opaque shared NT handle referencing a timeline semaphore
- See Also:
-
CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD
public static final int CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FDExternal semaphore handle types. (CUexternalSemaphoreHandleType)Enum values:
EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD- Handle is an opaque file descriptorEXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32- Handle is an opaque shared NT handleEXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT- Handle is an opaque, globally shared handleEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE- Handle is a shared NT handle referencing a D3D12 fence objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE- Handle is a shared NT handle referencing a D3D11 fence objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC- Opaque handle to NvSciSync ObjectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX- Handle is a shared NT handle referencing a D3D11 keyed mutex objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT- Handle is a globally shared handle referencing a D3D11 keyed mutex objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD- Handle is an opaque file descriptor referencing a timeline semaphoreEXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32- Handle is an opaque shared NT handle referencing a timeline semaphore
- See Also:
-
CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32
public static final int CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32External semaphore handle types. (CUexternalSemaphoreHandleType)Enum values:
EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD- Handle is an opaque file descriptorEXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32- Handle is an opaque shared NT handleEXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT- Handle is an opaque, globally shared handleEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE- Handle is a shared NT handle referencing a D3D12 fence objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE- Handle is a shared NT handle referencing a D3D11 fence objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC- Opaque handle to NvSciSync ObjectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX- Handle is a shared NT handle referencing a D3D11 keyed mutex objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT- Handle is a globally shared handle referencing a D3D11 keyed mutex objectEXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD- Handle is an opaque file descriptor referencing a timeline semaphoreEXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32- Handle is an opaque shared NT handle referencing a timeline semaphore
- See Also:
-
CU_MEM_HANDLE_TYPE_NONE
public static final int CU_MEM_HANDLE_TYPE_NONEFlags for specifying particular handle types. (CUmemAllocationHandleType)Enum values:
MEM_HANDLE_TYPE_NONE- Does not allow any export mechanism.MEM_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR- Allows a file descriptor to be used for exporting. Permitted only on POSIX systems. (int)MEM_HANDLE_TYPE_WIN32- Allows a Win32 NT handle to be used for exporting. (HANDLE)MEM_HANDLE_TYPE_WIN32_KMT- Allows a Win32 KMT handle to be used for exporting. (D3DKMT_HANDLE)
- See Also:
-
CU_MEM_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR
public static final int CU_MEM_HANDLE_TYPE_POSIX_FILE_DESCRIPTORFlags for specifying particular handle types. (CUmemAllocationHandleType)Enum values:
MEM_HANDLE_TYPE_NONE- Does not allow any export mechanism.MEM_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR- Allows a file descriptor to be used for exporting. Permitted only on POSIX systems. (int)MEM_HANDLE_TYPE_WIN32- Allows a Win32 NT handle to be used for exporting. (HANDLE)MEM_HANDLE_TYPE_WIN32_KMT- Allows a Win32 KMT handle to be used for exporting. (D3DKMT_HANDLE)
- See Also:
-
CU_MEM_HANDLE_TYPE_WIN32
public static final int CU_MEM_HANDLE_TYPE_WIN32Flags for specifying particular handle types. (CUmemAllocationHandleType)Enum values:
MEM_HANDLE_TYPE_NONE- Does not allow any export mechanism.MEM_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR- Allows a file descriptor to be used for exporting. Permitted only on POSIX systems. (int)MEM_HANDLE_TYPE_WIN32- Allows a Win32 NT handle to be used for exporting. (HANDLE)MEM_HANDLE_TYPE_WIN32_KMT- Allows a Win32 KMT handle to be used for exporting. (D3DKMT_HANDLE)
- See Also:
-
CU_MEM_HANDLE_TYPE_WIN32_KMT
public static final int CU_MEM_HANDLE_TYPE_WIN32_KMTFlags for specifying particular handle types. (CUmemAllocationHandleType)Enum values:
MEM_HANDLE_TYPE_NONE- Does not allow any export mechanism.MEM_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR- Allows a file descriptor to be used for exporting. Permitted only on POSIX systems. (int)MEM_HANDLE_TYPE_WIN32- Allows a Win32 NT handle to be used for exporting. (HANDLE)MEM_HANDLE_TYPE_WIN32_KMT- Allows a Win32 KMT handle to be used for exporting. (D3DKMT_HANDLE)
- See Also:
-
CU_MEM_ACCESS_FLAGS_PROT_NONE
public static final int CU_MEM_ACCESS_FLAGS_PROT_NONESpecifies the memory protection flags for mapping. (CUmemAccess_flags)Enum values:
MEM_ACCESS_FLAGS_PROT_NONE- Default, make the address range not accessibleMEM_ACCESS_FLAGS_PROT_READ- Make the address range read accessibleMEM_ACCESS_FLAGS_PROT_READWRITE- Make the address range read-write accessible
- See Also:
-
CU_MEM_ACCESS_FLAGS_PROT_READ
public static final int CU_MEM_ACCESS_FLAGS_PROT_READSpecifies the memory protection flags for mapping. (CUmemAccess_flags)Enum values:
MEM_ACCESS_FLAGS_PROT_NONE- Default, make the address range not accessibleMEM_ACCESS_FLAGS_PROT_READ- Make the address range read accessibleMEM_ACCESS_FLAGS_PROT_READWRITE- Make the address range read-write accessible
- See Also:
-
CU_MEM_ACCESS_FLAGS_PROT_READWRITE
public static final int CU_MEM_ACCESS_FLAGS_PROT_READWRITESpecifies the memory protection flags for mapping. (CUmemAccess_flags)Enum values:
MEM_ACCESS_FLAGS_PROT_NONE- Default, make the address range not accessibleMEM_ACCESS_FLAGS_PROT_READ- Make the address range read accessibleMEM_ACCESS_FLAGS_PROT_READWRITE- Make the address range read-write accessible
- See Also:
-
CU_MEM_LOCATION_TYPE_INVALID
public static final int CU_MEM_LOCATION_TYPE_INVALIDSpecifies the type of location. (CUmemLocationType)Enum values:
MEM_LOCATION_TYPE_INVALIDMEM_LOCATION_TYPE_DEVICE- Location is a device location, thus id is a device ordinal
- See Also:
-
CU_MEM_LOCATION_TYPE_DEVICE
public static final int CU_MEM_LOCATION_TYPE_DEVICESpecifies the type of location. (CUmemLocationType)Enum values:
MEM_LOCATION_TYPE_INVALIDMEM_LOCATION_TYPE_DEVICE- Location is a device location, thus id is a device ordinal
- See Also:
-
CU_MEM_ALLOCATION_TYPE_INVALID
public static final int CU_MEM_ALLOCATION_TYPE_INVALIDDefines the allocation types available. (CUmemAllocationType)Enum values:
MEM_ALLOCATION_TYPE_INVALIDMEM_ALLOCATION_TYPE_PINNED- This allocation type is 'pinned', i.e. cannot migrate from its current location while the application is actively using it
- See Also:
-
CU_MEM_ALLOCATION_TYPE_PINNED
public static final int CU_MEM_ALLOCATION_TYPE_PINNEDDefines the allocation types available. (CUmemAllocationType)Enum values:
MEM_ALLOCATION_TYPE_INVALIDMEM_ALLOCATION_TYPE_PINNED- This allocation type is 'pinned', i.e. cannot migrate from its current location while the application is actively using it
- See Also:
-
CU_MEM_ALLOC_GRANULARITY_MINIMUM
public static final int CU_MEM_ALLOC_GRANULARITY_MINIMUMFlag for requesting different optimal and required granularities for an allocation. (CUmemAllocationGranularity_flags)Enum values:
MEM_ALLOC_GRANULARITY_MINIMUM- Minimum required granularity for allocationMEM_ALLOC_GRANULARITY_RECOMMENDED- Recommended granularity for allocation for best performance
- See Also:
-
CU_MEM_ALLOC_GRANULARITY_RECOMMENDED
public static final int CU_MEM_ALLOC_GRANULARITY_RECOMMENDEDFlag for requesting different optimal and required granularities for an allocation. (CUmemAllocationGranularity_flags)Enum values:
MEM_ALLOC_GRANULARITY_MINIMUM- Minimum required granularity for allocationMEM_ALLOC_GRANULARITY_RECOMMENDED- Recommended granularity for allocation for best performance
- See Also:
-
CU_ARRAY_SPARSE_SUBRESOURCE_TYPE_SPARSE_LEVEL
public static final int CU_ARRAY_SPARSE_SUBRESOURCE_TYPE_SPARSE_LEVELSparse subresource types. (CUarraySparseSubresourceType)Enum values:
- See Also:
-
CU_ARRAY_SPARSE_SUBRESOURCE_TYPE_MIPTAIL
public static final int CU_ARRAY_SPARSE_SUBRESOURCE_TYPE_MIPTAILSparse subresource types. (CUarraySparseSubresourceType)Enum values:
- See Also:
-
CU_MEM_OPERATION_TYPE_MAP
public static final int CU_MEM_OPERATION_TYPE_MAPMemory operation types. (CUmemOperationType)Enum values:
- See Also:
-
CU_MEM_OPERATION_TYPE_UNMAP
public static final int CU_MEM_OPERATION_TYPE_UNMAPMemory operation types. (CUmemOperationType)Enum values:
- See Also:
-
CU_MEM_HANDLE_TYPE_GENERIC
public static final int CU_MEM_HANDLE_TYPE_GENERICMemory handle types (CUmemHandleType)- See Also:
-
CU_MEM_ALLOCATION_COMP_NONE
public static final int CU_MEM_ALLOCATION_COMP_NONESpecifies compression attribute for an allocation. (CUmemAllocationCompType)Enum values:
MEM_ALLOCATION_COMP_NONE- Allocating non-compressible memoryMEM_ALLOCATION_COMP_GENERIC- Allocating compressible memory
- See Also:
-
CU_MEM_ALLOCATION_COMP_GENERIC
public static final int CU_MEM_ALLOCATION_COMP_GENERICSpecifies compression attribute for an allocation. (CUmemAllocationCompType)Enum values:
MEM_ALLOCATION_COMP_NONE- Allocating non-compressible memoryMEM_ALLOCATION_COMP_GENERIC- Allocating compressible memory
- See Also:
-
CU_MEM_CREATE_USAGE_TILE_POOL
public static final int CU_MEM_CREATE_USAGE_TILE_POOLThis flag if set indicates that the memory will be used as a tile pool.- See Also:
-
CU_GRAPH_EXEC_UPDATE_SUCCESS
public static final int CU_GRAPH_EXEC_UPDATE_SUCCESSCUgraphExecUpdateResultEnum values:
GRAPH_EXEC_UPDATE_SUCCESS- The update succeededGRAPH_EXEC_UPDATE_ERROR- The update failed for an unexpected reason which is described in the return value of the functionGRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGED- The update failed because the topology changedGRAPH_EXEC_UPDATE_ERROR_NODE_TYPE_CHANGED- The update failed because a node type changedGRAPH_EXEC_UPDATE_ERROR_FUNCTION_CHANGED- The update failed because the function of a kernel node changed (CUDA driver <11.2)GRAPH_EXEC_UPDATE_ERROR_PARAMETERS_CHANGED- The update failed because the parameters changed in a way that is not supportedGRAPH_EXEC_UPDATE_ERROR_NOT_SUPPORTED- The update failed because something about the node is not supportedGRAPH_EXEC_UPDATE_ERROR_UNSUPPORTED_FUNCTION_CHANGE- The update failed because the function of a kernel node changed in an unsupported way
- See Also:
-
CU_GRAPH_EXEC_UPDATE_ERROR
public static final int CU_GRAPH_EXEC_UPDATE_ERRORCUgraphExecUpdateResultEnum values:
GRAPH_EXEC_UPDATE_SUCCESS- The update succeededGRAPH_EXEC_UPDATE_ERROR- The update failed for an unexpected reason which is described in the return value of the functionGRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGED- The update failed because the topology changedGRAPH_EXEC_UPDATE_ERROR_NODE_TYPE_CHANGED- The update failed because a node type changedGRAPH_EXEC_UPDATE_ERROR_FUNCTION_CHANGED- The update failed because the function of a kernel node changed (CUDA driver <11.2)GRAPH_EXEC_UPDATE_ERROR_PARAMETERS_CHANGED- The update failed because the parameters changed in a way that is not supportedGRAPH_EXEC_UPDATE_ERROR_NOT_SUPPORTED- The update failed because something about the node is not supportedGRAPH_EXEC_UPDATE_ERROR_UNSUPPORTED_FUNCTION_CHANGE- The update failed because the function of a kernel node changed in an unsupported way
- See Also:
-
CU_GRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGED
public static final int CU_GRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGEDCUgraphExecUpdateResultEnum values:
GRAPH_EXEC_UPDATE_SUCCESS- The update succeededGRAPH_EXEC_UPDATE_ERROR- The update failed for an unexpected reason which is described in the return value of the functionGRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGED- The update failed because the topology changedGRAPH_EXEC_UPDATE_ERROR_NODE_TYPE_CHANGED- The update failed because a node type changedGRAPH_EXEC_UPDATE_ERROR_FUNCTION_CHANGED- The update failed because the function of a kernel node changed (CUDA driver <11.2)GRAPH_EXEC_UPDATE_ERROR_PARAMETERS_CHANGED- The update failed because the parameters changed in a way that is not supportedGRAPH_EXEC_UPDATE_ERROR_NOT_SUPPORTED- The update failed because something about the node is not supportedGRAPH_EXEC_UPDATE_ERROR_UNSUPPORTED_FUNCTION_CHANGE- The update failed because the function of a kernel node changed in an unsupported way
- See Also:
-
CU_GRAPH_EXEC_UPDATE_ERROR_NODE_TYPE_CHANGED
public static final int CU_GRAPH_EXEC_UPDATE_ERROR_NODE_TYPE_CHANGEDCUgraphExecUpdateResultEnum values:
GRAPH_EXEC_UPDATE_SUCCESS- The update succeededGRAPH_EXEC_UPDATE_ERROR- The update failed for an unexpected reason which is described in the return value of the functionGRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGED- The update failed because the topology changedGRAPH_EXEC_UPDATE_ERROR_NODE_TYPE_CHANGED- The update failed because a node type changedGRAPH_EXEC_UPDATE_ERROR_FUNCTION_CHANGED- The update failed because the function of a kernel node changed (CUDA driver <11.2)GRAPH_EXEC_UPDATE_ERROR_PARAMETERS_CHANGED- The update failed because the parameters changed in a way that is not supportedGRAPH_EXEC_UPDATE_ERROR_NOT_SUPPORTED- The update failed because something about the node is not supportedGRAPH_EXEC_UPDATE_ERROR_UNSUPPORTED_FUNCTION_CHANGE- The update failed because the function of a kernel node changed in an unsupported way
- See Also:
-
CU_GRAPH_EXEC_UPDATE_ERROR_FUNCTION_CHANGED
public static final int CU_GRAPH_EXEC_UPDATE_ERROR_FUNCTION_CHANGEDCUgraphExecUpdateResultEnum values:
GRAPH_EXEC_UPDATE_SUCCESS- The update succeededGRAPH_EXEC_UPDATE_ERROR- The update failed for an unexpected reason which is described in the return value of the functionGRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGED- The update failed because the topology changedGRAPH_EXEC_UPDATE_ERROR_NODE_TYPE_CHANGED- The update failed because a node type changedGRAPH_EXEC_UPDATE_ERROR_FUNCTION_CHANGED- The update failed because the function of a kernel node changed (CUDA driver <11.2)GRAPH_EXEC_UPDATE_ERROR_PARAMETERS_CHANGED- The update failed because the parameters changed in a way that is not supportedGRAPH_EXEC_UPDATE_ERROR_NOT_SUPPORTED- The update failed because something about the node is not supportedGRAPH_EXEC_UPDATE_ERROR_UNSUPPORTED_FUNCTION_CHANGE- The update failed because the function of a kernel node changed in an unsupported way
- See Also:
-
CU_GRAPH_EXEC_UPDATE_ERROR_PARAMETERS_CHANGED
public static final int CU_GRAPH_EXEC_UPDATE_ERROR_PARAMETERS_CHANGEDCUgraphExecUpdateResultEnum values:
GRAPH_EXEC_UPDATE_SUCCESS- The update succeededGRAPH_EXEC_UPDATE_ERROR- The update failed for an unexpected reason which is described in the return value of the functionGRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGED- The update failed because the topology changedGRAPH_EXEC_UPDATE_ERROR_NODE_TYPE_CHANGED- The update failed because a node type changedGRAPH_EXEC_UPDATE_ERROR_FUNCTION_CHANGED- The update failed because the function of a kernel node changed (CUDA driver <11.2)GRAPH_EXEC_UPDATE_ERROR_PARAMETERS_CHANGED- The update failed because the parameters changed in a way that is not supportedGRAPH_EXEC_UPDATE_ERROR_NOT_SUPPORTED- The update failed because something about the node is not supportedGRAPH_EXEC_UPDATE_ERROR_UNSUPPORTED_FUNCTION_CHANGE- The update failed because the function of a kernel node changed in an unsupported way
- See Also:
-
CU_GRAPH_EXEC_UPDATE_ERROR_NOT_SUPPORTED
public static final int CU_GRAPH_EXEC_UPDATE_ERROR_NOT_SUPPORTEDCUgraphExecUpdateResultEnum values:
GRAPH_EXEC_UPDATE_SUCCESS- The update succeededGRAPH_EXEC_UPDATE_ERROR- The update failed for an unexpected reason which is described in the return value of the functionGRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGED- The update failed because the topology changedGRAPH_EXEC_UPDATE_ERROR_NODE_TYPE_CHANGED- The update failed because a node type changedGRAPH_EXEC_UPDATE_ERROR_FUNCTION_CHANGED- The update failed because the function of a kernel node changed (CUDA driver <11.2)GRAPH_EXEC_UPDATE_ERROR_PARAMETERS_CHANGED- The update failed because the parameters changed in a way that is not supportedGRAPH_EXEC_UPDATE_ERROR_NOT_SUPPORTED- The update failed because something about the node is not supportedGRAPH_EXEC_UPDATE_ERROR_UNSUPPORTED_FUNCTION_CHANGE- The update failed because the function of a kernel node changed in an unsupported way
- See Also:
-
CU_GRAPH_EXEC_UPDATE_ERROR_UNSUPPORTED_FUNCTION_CHANGE
public static final int CU_GRAPH_EXEC_UPDATE_ERROR_UNSUPPORTED_FUNCTION_CHANGECUgraphExecUpdateResultEnum values:
GRAPH_EXEC_UPDATE_SUCCESS- The update succeededGRAPH_EXEC_UPDATE_ERROR- The update failed for an unexpected reason which is described in the return value of the functionGRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGED- The update failed because the topology changedGRAPH_EXEC_UPDATE_ERROR_NODE_TYPE_CHANGED- The update failed because a node type changedGRAPH_EXEC_UPDATE_ERROR_FUNCTION_CHANGED- The update failed because the function of a kernel node changed (CUDA driver <11.2)GRAPH_EXEC_UPDATE_ERROR_PARAMETERS_CHANGED- The update failed because the parameters changed in a way that is not supportedGRAPH_EXEC_UPDATE_ERROR_NOT_SUPPORTED- The update failed because something about the node is not supportedGRAPH_EXEC_UPDATE_ERROR_UNSUPPORTED_FUNCTION_CHANGE- The update failed because the function of a kernel node changed in an unsupported way
- See Also:
-
CU_MEMPOOL_ATTR_REUSE_FOLLOW_EVENT_DEPENDENCIES
public static final int CU_MEMPOOL_ATTR_REUSE_FOLLOW_EVENT_DEPENDENCIESCUDA memory pool attributes (CUmemPool_attribute)Enum values:
MEMPOOL_ATTR_REUSE_FOLLOW_EVENT_DEPENDENCIES- AllowMemAllocAsyncto use memory asynchronously freed in another streams as long as a stream ordering dependency of the allocating stream on the free action exists. Cuda events and null stream interactions can create the required stream ordered dependencies.(value type =
int, default enabled)MEMPOOL_ATTR_REUSE_ALLOW_OPPORTUNISTIC- Allow reuse of already completed frees when there is no dependency between the free and allocation. (value type =int, default enabled)MEMPOOL_ATTR_REUSE_ALLOW_INTERNAL_DEPENDENCIES- AllowMemAllocAsyncto insert new stream dependencies in order to establish the stream ordering required to reuse a piece of memory released byMemFreeAsync.(value type =
int, default enabled).MEMPOOL_ATTR_RELEASE_THRESHOLD- Amount of reserved memory in bytes to hold onto before trying to release memory back to the OS.When more than the release threshold bytes of memory are held by the memory pool, the allocator will try to release memory back to the OS on the next call to stream, event or context synchronize.
(value type =
cuuint64_t, default 0)MEMPOOL_ATTR_RESERVED_MEM_CURRENT- Amount of backing memory currently allocated for the mempool. (value type =cuuint64_t)MEMPOOL_ATTR_RESERVED_MEM_HIGH- High watermark of backing memory allocated for themempoolsince the last time it was reset. High watermark can only be reset to zero.(value type =
cuuint64_t)MEMPOOL_ATTR_USED_MEM_CURRENT- Amount of memory from the pool that is currently in use by the application (value type =cuuint64_t).MEMPOOL_ATTR_USED_MEM_HIGH- High watermark of the amount of memory from the pool that was in use by the application since the last time it was reset. High watermark can only be reset to zero.(value type =
cuuint64_t)
- See Also:
-
CU_MEMPOOL_ATTR_REUSE_ALLOW_OPPORTUNISTIC
public static final int CU_MEMPOOL_ATTR_REUSE_ALLOW_OPPORTUNISTICCUDA memory pool attributes (CUmemPool_attribute)Enum values:
MEMPOOL_ATTR_REUSE_FOLLOW_EVENT_DEPENDENCIES- AllowMemAllocAsyncto use memory asynchronously freed in another streams as long as a stream ordering dependency of the allocating stream on the free action exists. Cuda events and null stream interactions can create the required stream ordered dependencies.(value type =
int, default enabled)MEMPOOL_ATTR_REUSE_ALLOW_OPPORTUNISTIC- Allow reuse of already completed frees when there is no dependency between the free and allocation. (value type =int, default enabled)MEMPOOL_ATTR_REUSE_ALLOW_INTERNAL_DEPENDENCIES- AllowMemAllocAsyncto insert new stream dependencies in order to establish the stream ordering required to reuse a piece of memory released byMemFreeAsync.(value type =
int, default enabled).MEMPOOL_ATTR_RELEASE_THRESHOLD- Amount of reserved memory in bytes to hold onto before trying to release memory back to the OS.When more than the release threshold bytes of memory are held by the memory pool, the allocator will try to release memory back to the OS on the next call to stream, event or context synchronize.
(value type =
cuuint64_t, default 0)MEMPOOL_ATTR_RESERVED_MEM_CURRENT- Amount of backing memory currently allocated for the mempool. (value type =cuuint64_t)MEMPOOL_ATTR_RESERVED_MEM_HIGH- High watermark of backing memory allocated for themempoolsince the last time it was reset. High watermark can only be reset to zero.(value type =
cuuint64_t)MEMPOOL_ATTR_USED_MEM_CURRENT- Amount of memory from the pool that is currently in use by the application (value type =cuuint64_t).MEMPOOL_ATTR_USED_MEM_HIGH- High watermark of the amount of memory from the pool that was in use by the application since the last time it was reset. High watermark can only be reset to zero.(value type =
cuuint64_t)
- See Also:
-
CU_MEMPOOL_ATTR_REUSE_ALLOW_INTERNAL_DEPENDENCIES
public static final int CU_MEMPOOL_ATTR_REUSE_ALLOW_INTERNAL_DEPENDENCIESCUDA memory pool attributes (CUmemPool_attribute)Enum values:
MEMPOOL_ATTR_REUSE_FOLLOW_EVENT_DEPENDENCIES- AllowMemAllocAsyncto use memory asynchronously freed in another streams as long as a stream ordering dependency of the allocating stream on the free action exists. Cuda events and null stream interactions can create the required stream ordered dependencies.(value type =
int, default enabled)MEMPOOL_ATTR_REUSE_ALLOW_OPPORTUNISTIC- Allow reuse of already completed frees when there is no dependency between the free and allocation. (value type =int, default enabled)MEMPOOL_ATTR_REUSE_ALLOW_INTERNAL_DEPENDENCIES- AllowMemAllocAsyncto insert new stream dependencies in order to establish the stream ordering required to reuse a piece of memory released byMemFreeAsync.(value type =
int, default enabled).MEMPOOL_ATTR_RELEASE_THRESHOLD- Amount of reserved memory in bytes to hold onto before trying to release memory back to the OS.When more than the release threshold bytes of memory are held by the memory pool, the allocator will try to release memory back to the OS on the next call to stream, event or context synchronize.
(value type =
cuuint64_t, default 0)MEMPOOL_ATTR_RESERVED_MEM_CURRENT- Amount of backing memory currently allocated for the mempool. (value type =cuuint64_t)MEMPOOL_ATTR_RESERVED_MEM_HIGH- High watermark of backing memory allocated for themempoolsince the last time it was reset. High watermark can only be reset to zero.(value type =
cuuint64_t)MEMPOOL_ATTR_USED_MEM_CURRENT- Amount of memory from the pool that is currently in use by the application (value type =cuuint64_t).MEMPOOL_ATTR_USED_MEM_HIGH- High watermark of the amount of memory from the pool that was in use by the application since the last time it was reset. High watermark can only be reset to zero.(value type =
cuuint64_t)
- See Also:
-
CU_MEMPOOL_ATTR_RELEASE_THRESHOLD
public static final int CU_MEMPOOL_ATTR_RELEASE_THRESHOLDCUDA memory pool attributes (CUmemPool_attribute)Enum values:
MEMPOOL_ATTR_REUSE_FOLLOW_EVENT_DEPENDENCIES- AllowMemAllocAsyncto use memory asynchronously freed in another streams as long as a stream ordering dependency of the allocating stream on the free action exists. Cuda events and null stream interactions can create the required stream ordered dependencies.(value type =
int, default enabled)MEMPOOL_ATTR_REUSE_ALLOW_OPPORTUNISTIC- Allow reuse of already completed frees when there is no dependency between the free and allocation. (value type =int, default enabled)MEMPOOL_ATTR_REUSE_ALLOW_INTERNAL_DEPENDENCIES- AllowMemAllocAsyncto insert new stream dependencies in order to establish the stream ordering required to reuse a piece of memory released byMemFreeAsync.(value type =
int, default enabled).MEMPOOL_ATTR_RELEASE_THRESHOLD- Amount of reserved memory in bytes to hold onto before trying to release memory back to the OS.When more than the release threshold bytes of memory are held by the memory pool, the allocator will try to release memory back to the OS on the next call to stream, event or context synchronize.
(value type =
cuuint64_t, default 0)MEMPOOL_ATTR_RESERVED_MEM_CURRENT- Amount of backing memory currently allocated for the mempool. (value type =cuuint64_t)MEMPOOL_ATTR_RESERVED_MEM_HIGH- High watermark of backing memory allocated for themempoolsince the last time it was reset. High watermark can only be reset to zero.(value type =
cuuint64_t)MEMPOOL_ATTR_USED_MEM_CURRENT- Amount of memory from the pool that is currently in use by the application (value type =cuuint64_t).MEMPOOL_ATTR_USED_MEM_HIGH- High watermark of the amount of memory from the pool that was in use by the application since the last time it was reset. High watermark can only be reset to zero.(value type =
cuuint64_t)
- See Also:
-
CU_MEMPOOL_ATTR_RESERVED_MEM_CURRENT
public static final int CU_MEMPOOL_ATTR_RESERVED_MEM_CURRENTCUDA memory pool attributes (CUmemPool_attribute)Enum values:
MEMPOOL_ATTR_REUSE_FOLLOW_EVENT_DEPENDENCIES- AllowMemAllocAsyncto use memory asynchronously freed in another streams as long as a stream ordering dependency of the allocating stream on the free action exists. Cuda events and null stream interactions can create the required stream ordered dependencies.(value type =
int, default enabled)MEMPOOL_ATTR_REUSE_ALLOW_OPPORTUNISTIC- Allow reuse of already completed frees when there is no dependency between the free and allocation. (value type =int, default enabled)MEMPOOL_ATTR_REUSE_ALLOW_INTERNAL_DEPENDENCIES- AllowMemAllocAsyncto insert new stream dependencies in order to establish the stream ordering required to reuse a piece of memory released byMemFreeAsync.(value type =
int, default enabled).MEMPOOL_ATTR_RELEASE_THRESHOLD- Amount of reserved memory in bytes to hold onto before trying to release memory back to the OS.When more than the release threshold bytes of memory are held by the memory pool, the allocator will try to release memory back to the OS on the next call to stream, event or context synchronize.
(value type =
cuuint64_t, default 0)MEMPOOL_ATTR_RESERVED_MEM_CURRENT- Amount of backing memory currently allocated for the mempool. (value type =cuuint64_t)MEMPOOL_ATTR_RESERVED_MEM_HIGH- High watermark of backing memory allocated for themempoolsince the last time it was reset. High watermark can only be reset to zero.(value type =
cuuint64_t)MEMPOOL_ATTR_USED_MEM_CURRENT- Amount of memory from the pool that is currently in use by the application (value type =cuuint64_t).MEMPOOL_ATTR_USED_MEM_HIGH- High watermark of the amount of memory from the pool that was in use by the application since the last time it was reset. High watermark can only be reset to zero.(value type =
cuuint64_t)
- See Also:
-
CU_MEMPOOL_ATTR_RESERVED_MEM_HIGH
public static final int CU_MEMPOOL_ATTR_RESERVED_MEM_HIGHCUDA memory pool attributes (CUmemPool_attribute)Enum values:
MEMPOOL_ATTR_REUSE_FOLLOW_EVENT_DEPENDENCIES- AllowMemAllocAsyncto use memory asynchronously freed in another streams as long as a stream ordering dependency of the allocating stream on the free action exists. Cuda events and null stream interactions can create the required stream ordered dependencies.(value type =
int, default enabled)MEMPOOL_ATTR_REUSE_ALLOW_OPPORTUNISTIC- Allow reuse of already completed frees when there is no dependency between the free and allocation. (value type =int, default enabled)MEMPOOL_ATTR_REUSE_ALLOW_INTERNAL_DEPENDENCIES- AllowMemAllocAsyncto insert new stream dependencies in order to establish the stream ordering required to reuse a piece of memory released byMemFreeAsync.(value type =
int, default enabled).MEMPOOL_ATTR_RELEASE_THRESHOLD- Amount of reserved memory in bytes to hold onto before trying to release memory back to the OS.When more than the release threshold bytes of memory are held by the memory pool, the allocator will try to release memory back to the OS on the next call to stream, event or context synchronize.
(value type =
cuuint64_t, default 0)MEMPOOL_ATTR_RESERVED_MEM_CURRENT- Amount of backing memory currently allocated for the mempool. (value type =cuuint64_t)MEMPOOL_ATTR_RESERVED_MEM_HIGH- High watermark of backing memory allocated for themempoolsince the last time it was reset. High watermark can only be reset to zero.(value type =
cuuint64_t)MEMPOOL_ATTR_USED_MEM_CURRENT- Amount of memory from the pool that is currently in use by the application (value type =cuuint64_t).MEMPOOL_ATTR_USED_MEM_HIGH- High watermark of the amount of memory from the pool that was in use by the application since the last time it was reset. High watermark can only be reset to zero.(value type =
cuuint64_t)
- See Also:
-
CU_MEMPOOL_ATTR_USED_MEM_CURRENT
public static final int CU_MEMPOOL_ATTR_USED_MEM_CURRENTCUDA memory pool attributes (CUmemPool_attribute)Enum values:
MEMPOOL_ATTR_REUSE_FOLLOW_EVENT_DEPENDENCIES- AllowMemAllocAsyncto use memory asynchronously freed in another streams as long as a stream ordering dependency of the allocating stream on the free action exists. Cuda events and null stream interactions can create the required stream ordered dependencies.(value type =
int, default enabled)MEMPOOL_ATTR_REUSE_ALLOW_OPPORTUNISTIC- Allow reuse of already completed frees when there is no dependency between the free and allocation. (value type =int, default enabled)MEMPOOL_ATTR_REUSE_ALLOW_INTERNAL_DEPENDENCIES- AllowMemAllocAsyncto insert new stream dependencies in order to establish the stream ordering required to reuse a piece of memory released byMemFreeAsync.(value type =
int, default enabled).MEMPOOL_ATTR_RELEASE_THRESHOLD- Amount of reserved memory in bytes to hold onto before trying to release memory back to the OS.When more than the release threshold bytes of memory are held by the memory pool, the allocator will try to release memory back to the OS on the next call to stream, event or context synchronize.
(value type =
cuuint64_t, default 0)MEMPOOL_ATTR_RESERVED_MEM_CURRENT- Amount of backing memory currently allocated for the mempool. (value type =cuuint64_t)MEMPOOL_ATTR_RESERVED_MEM_HIGH- High watermark of backing memory allocated for themempoolsince the last time it was reset. High watermark can only be reset to zero.(value type =
cuuint64_t)MEMPOOL_ATTR_USED_MEM_CURRENT- Amount of memory from the pool that is currently in use by the application (value type =cuuint64_t).MEMPOOL_ATTR_USED_MEM_HIGH- High watermark of the amount of memory from the pool that was in use by the application since the last time it was reset. High watermark can only be reset to zero.(value type =
cuuint64_t)
- See Also:
-
CU_MEMPOOL_ATTR_USED_MEM_HIGH
public static final int CU_MEMPOOL_ATTR_USED_MEM_HIGHCUDA memory pool attributes (CUmemPool_attribute)Enum values:
MEMPOOL_ATTR_REUSE_FOLLOW_EVENT_DEPENDENCIES- AllowMemAllocAsyncto use memory asynchronously freed in another streams as long as a stream ordering dependency of the allocating stream on the free action exists. Cuda events and null stream interactions can create the required stream ordered dependencies.(value type =
int, default enabled)MEMPOOL_ATTR_REUSE_ALLOW_OPPORTUNISTIC- Allow reuse of already completed frees when there is no dependency between the free and allocation. (value type =int, default enabled)MEMPOOL_ATTR_REUSE_ALLOW_INTERNAL_DEPENDENCIES- AllowMemAllocAsyncto insert new stream dependencies in order to establish the stream ordering required to reuse a piece of memory released byMemFreeAsync.(value type =
int, default enabled).MEMPOOL_ATTR_RELEASE_THRESHOLD- Amount of reserved memory in bytes to hold onto before trying to release memory back to the OS.When more than the release threshold bytes of memory are held by the memory pool, the allocator will try to release memory back to the OS on the next call to stream, event or context synchronize.
(value type =
cuuint64_t, default 0)MEMPOOL_ATTR_RESERVED_MEM_CURRENT- Amount of backing memory currently allocated for the mempool. (value type =cuuint64_t)MEMPOOL_ATTR_RESERVED_MEM_HIGH- High watermark of backing memory allocated for themempoolsince the last time it was reset. High watermark can only be reset to zero.(value type =
cuuint64_t)MEMPOOL_ATTR_USED_MEM_CURRENT- Amount of memory from the pool that is currently in use by the application (value type =cuuint64_t).MEMPOOL_ATTR_USED_MEM_HIGH- High watermark of the amount of memory from the pool that was in use by the application since the last time it was reset. High watermark can only be reset to zero.(value type =
cuuint64_t)
- See Also:
-
CU_GRAPH_MEM_ATTR_USED_MEM_CURRENT
public static final int CU_GRAPH_MEM_ATTR_USED_MEM_CURRENTCUgraphMem_attributeEnum values:
GRAPH_MEM_ATTR_USED_MEM_CURRENT- (value type = cuuint64_t) Amount of memory, in bytes, currently associated with graphsGRAPH_MEM_ATTR_USED_MEM_HIGH- High watermark of memory, in bytes, associated with graphs since the last time it was reset. High watermark can only be reset to zero.(value type =
cuuint64_t)GRAPH_MEM_ATTR_RESERVED_MEM_CURRENT- Amount of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator. (value type =cuuint64_t)GRAPH_MEM_ATTR_RESERVED_MEM_HIGH- High watermark of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator. (value type =cuuint64_t)
- See Also:
-
CU_GRAPH_MEM_ATTR_USED_MEM_HIGH
public static final int CU_GRAPH_MEM_ATTR_USED_MEM_HIGHCUgraphMem_attributeEnum values:
GRAPH_MEM_ATTR_USED_MEM_CURRENT- (value type = cuuint64_t) Amount of memory, in bytes, currently associated with graphsGRAPH_MEM_ATTR_USED_MEM_HIGH- High watermark of memory, in bytes, associated with graphs since the last time it was reset. High watermark can only be reset to zero.(value type =
cuuint64_t)GRAPH_MEM_ATTR_RESERVED_MEM_CURRENT- Amount of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator. (value type =cuuint64_t)GRAPH_MEM_ATTR_RESERVED_MEM_HIGH- High watermark of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator. (value type =cuuint64_t)
- See Also:
-
CU_GRAPH_MEM_ATTR_RESERVED_MEM_CURRENT
public static final int CU_GRAPH_MEM_ATTR_RESERVED_MEM_CURRENTCUgraphMem_attributeEnum values:
GRAPH_MEM_ATTR_USED_MEM_CURRENT- (value type = cuuint64_t) Amount of memory, in bytes, currently associated with graphsGRAPH_MEM_ATTR_USED_MEM_HIGH- High watermark of memory, in bytes, associated with graphs since the last time it was reset. High watermark can only be reset to zero.(value type =
cuuint64_t)GRAPH_MEM_ATTR_RESERVED_MEM_CURRENT- Amount of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator. (value type =cuuint64_t)GRAPH_MEM_ATTR_RESERVED_MEM_HIGH- High watermark of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator. (value type =cuuint64_t)
- See Also:
-
CU_GRAPH_MEM_ATTR_RESERVED_MEM_HIGH
public static final int CU_GRAPH_MEM_ATTR_RESERVED_MEM_HIGHCUgraphMem_attributeEnum values:
GRAPH_MEM_ATTR_USED_MEM_CURRENT- (value type = cuuint64_t) Amount of memory, in bytes, currently associated with graphsGRAPH_MEM_ATTR_USED_MEM_HIGH- High watermark of memory, in bytes, associated with graphs since the last time it was reset. High watermark can only be reset to zero.(value type =
cuuint64_t)GRAPH_MEM_ATTR_RESERVED_MEM_CURRENT- Amount of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator. (value type =cuuint64_t)GRAPH_MEM_ATTR_RESERVED_MEM_HIGH- High watermark of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator. (value type =cuuint64_t)
- See Also:
-
CU_CUDA_COOPERATIVE_LAUNCH_MULTI_DEVICE_NO_PRE_LAUNCH_SYNC
public static final int CU_CUDA_COOPERATIVE_LAUNCH_MULTI_DEVICE_NO_PRE_LAUNCH_SYNCEnum values:
CUDA_COOPERATIVE_LAUNCH_MULTI_DEVICE_NO_PRE_LAUNCH_SYNC- If set, each kernel launched as part ofLaunchCooperativeKernelMultiDeviceonly waits for prior work in the stream corresponding to that GPU to complete before the kernel begins execution.CUDA_COOPERATIVE_LAUNCH_MULTI_DEVICE_NO_POST_LAUNCH_SYNC- If set, any subsequent work pushed in a stream that participated in a call toLaunchCooperativeKernelMultiDevicewill only wait for the kernel launched on the GPU corresponding to that stream to complete before it begins execution.
- See Also:
-
CU_CUDA_COOPERATIVE_LAUNCH_MULTI_DEVICE_NO_POST_LAUNCH_SYNC
public static final int CU_CUDA_COOPERATIVE_LAUNCH_MULTI_DEVICE_NO_POST_LAUNCH_SYNCEnum values:
CUDA_COOPERATIVE_LAUNCH_MULTI_DEVICE_NO_PRE_LAUNCH_SYNC- If set, each kernel launched as part ofLaunchCooperativeKernelMultiDeviceonly waits for prior work in the stream corresponding to that GPU to complete before the kernel begins execution.CUDA_COOPERATIVE_LAUNCH_MULTI_DEVICE_NO_POST_LAUNCH_SYNC- If set, any subsequent work pushed in a stream that participated in a call toLaunchCooperativeKernelMultiDevicewill only wait for the kernel launched on the GPU corresponding to that stream to complete before it begins execution.
- See Also:
-
CUDA_ARRAY3D_LAYERED
public static final int CUDA_ARRAY3D_LAYEREDEnum values:
CUDA_ARRAY3D_LAYERED- If set, the CUDA array is a collection of layers, where each layer is either a 1D or a 2D array and the Depth member ofCUDA_ARRAY3D_DESCRIPTORspecifies the number of layers, not the depth of a 3D array.CUDA_ARRAY3D_2DARRAY- Deprecated, useCUDA_ARRAY3D_LAYERED.CUDA_ARRAY3D_SURFACE_LDST- This flag must be set in order to bind a surface reference to the CUDA array.CUDA_ARRAY3D_CUBEMAP- If set, the CUDA array is a collection of six 2D arrays, representing faces of a cube. The width of such a CUDA array must be equal to its height, and Depth must be six. IfCUDA_ARRAY3D_LAYEREDflag is also set, then the CUDA array is a collection of cubemaps and Depth must be a multiple of six.CUDA_ARRAY3D_TEXTURE_GATHER- This flag must be set in order to perform texture gather operations on a CUDA array.CUDA_ARRAY3D_DEPTH_TEXTURE- This flag if set indicates that the CUDA array is a DEPTH_TEXTURE.CUDA_ARRAY3D_COLOR_ATTACHMENT- This flag indicates that the CUDA array may be bound as a color target in an external graphics API.CUDA_ARRAY3D_SPARSE- This flag if set indicates that the CUDA array or CUDA mipmapped array is a sparse CUDA array or CUDA mipmapped array respectively
- See Also:
-
CUDA_ARRAY3D_2DARRAY
public static final int CUDA_ARRAY3D_2DARRAYEnum values:
CUDA_ARRAY3D_LAYERED- If set, the CUDA array is a collection of layers, where each layer is either a 1D or a 2D array and the Depth member ofCUDA_ARRAY3D_DESCRIPTORspecifies the number of layers, not the depth of a 3D array.CUDA_ARRAY3D_2DARRAY- Deprecated, useCUDA_ARRAY3D_LAYERED.CUDA_ARRAY3D_SURFACE_LDST- This flag must be set in order to bind a surface reference to the CUDA array.CUDA_ARRAY3D_CUBEMAP- If set, the CUDA array is a collection of six 2D arrays, representing faces of a cube. The width of such a CUDA array must be equal to its height, and Depth must be six. IfCUDA_ARRAY3D_LAYEREDflag is also set, then the CUDA array is a collection of cubemaps and Depth must be a multiple of six.CUDA_ARRAY3D_TEXTURE_GATHER- This flag must be set in order to perform texture gather operations on a CUDA array.CUDA_ARRAY3D_DEPTH_TEXTURE- This flag if set indicates that the CUDA array is a DEPTH_TEXTURE.CUDA_ARRAY3D_COLOR_ATTACHMENT- This flag indicates that the CUDA array may be bound as a color target in an external graphics API.CUDA_ARRAY3D_SPARSE- This flag if set indicates that the CUDA array or CUDA mipmapped array is a sparse CUDA array or CUDA mipmapped array respectively
- See Also:
-
CUDA_ARRAY3D_SURFACE_LDST
public static final int CUDA_ARRAY3D_SURFACE_LDSTEnum values:
CUDA_ARRAY3D_LAYERED- If set, the CUDA array is a collection of layers, where each layer is either a 1D or a 2D array and the Depth member ofCUDA_ARRAY3D_DESCRIPTORspecifies the number of layers, not the depth of a 3D array.CUDA_ARRAY3D_2DARRAY- Deprecated, useCUDA_ARRAY3D_LAYERED.CUDA_ARRAY3D_SURFACE_LDST- This flag must be set in order to bind a surface reference to the CUDA array.CUDA_ARRAY3D_CUBEMAP- If set, the CUDA array is a collection of six 2D arrays, representing faces of a cube. The width of such a CUDA array must be equal to its height, and Depth must be six. IfCUDA_ARRAY3D_LAYEREDflag is also set, then the CUDA array is a collection of cubemaps and Depth must be a multiple of six.CUDA_ARRAY3D_TEXTURE_GATHER- This flag must be set in order to perform texture gather operations on a CUDA array.CUDA_ARRAY3D_DEPTH_TEXTURE- This flag if set indicates that the CUDA array is a DEPTH_TEXTURE.CUDA_ARRAY3D_COLOR_ATTACHMENT- This flag indicates that the CUDA array may be bound as a color target in an external graphics API.CUDA_ARRAY3D_SPARSE- This flag if set indicates that the CUDA array or CUDA mipmapped array is a sparse CUDA array or CUDA mipmapped array respectively
- See Also:
-
CUDA_ARRAY3D_CUBEMAP
public static final int CUDA_ARRAY3D_CUBEMAPEnum values:
CUDA_ARRAY3D_LAYERED- If set, the CUDA array is a collection of layers, where each layer is either a 1D or a 2D array and the Depth member ofCUDA_ARRAY3D_DESCRIPTORspecifies the number of layers, not the depth of a 3D array.CUDA_ARRAY3D_2DARRAY- Deprecated, useCUDA_ARRAY3D_LAYERED.CUDA_ARRAY3D_SURFACE_LDST- This flag must be set in order to bind a surface reference to the CUDA array.CUDA_ARRAY3D_CUBEMAP- If set, the CUDA array is a collection of six 2D arrays, representing faces of a cube. The width of such a CUDA array must be equal to its height, and Depth must be six. IfCUDA_ARRAY3D_LAYEREDflag is also set, then the CUDA array is a collection of cubemaps and Depth must be a multiple of six.CUDA_ARRAY3D_TEXTURE_GATHER- This flag must be set in order to perform texture gather operations on a CUDA array.CUDA_ARRAY3D_DEPTH_TEXTURE- This flag if set indicates that the CUDA array is a DEPTH_TEXTURE.CUDA_ARRAY3D_COLOR_ATTACHMENT- This flag indicates that the CUDA array may be bound as a color target in an external graphics API.CUDA_ARRAY3D_SPARSE- This flag if set indicates that the CUDA array or CUDA mipmapped array is a sparse CUDA array or CUDA mipmapped array respectively
- See Also:
-
CUDA_ARRAY3D_TEXTURE_GATHER
public static final int CUDA_ARRAY3D_TEXTURE_GATHEREnum values:
CUDA_ARRAY3D_LAYERED- If set, the CUDA array is a collection of layers, where each layer is either a 1D or a 2D array and the Depth member ofCUDA_ARRAY3D_DESCRIPTORspecifies the number of layers, not the depth of a 3D array.CUDA_ARRAY3D_2DARRAY- Deprecated, useCUDA_ARRAY3D_LAYERED.CUDA_ARRAY3D_SURFACE_LDST- This flag must be set in order to bind a surface reference to the CUDA array.CUDA_ARRAY3D_CUBEMAP- If set, the CUDA array is a collection of six 2D arrays, representing faces of a cube. The width of such a CUDA array must be equal to its height, and Depth must be six. IfCUDA_ARRAY3D_LAYEREDflag is also set, then the CUDA array is a collection of cubemaps and Depth must be a multiple of six.CUDA_ARRAY3D_TEXTURE_GATHER- This flag must be set in order to perform texture gather operations on a CUDA array.CUDA_ARRAY3D_DEPTH_TEXTURE- This flag if set indicates that the CUDA array is a DEPTH_TEXTURE.CUDA_ARRAY3D_COLOR_ATTACHMENT- This flag indicates that the CUDA array may be bound as a color target in an external graphics API.CUDA_ARRAY3D_SPARSE- This flag if set indicates that the CUDA array or CUDA mipmapped array is a sparse CUDA array or CUDA mipmapped array respectively
- See Also:
-
CUDA_ARRAY3D_DEPTH_TEXTURE
public static final int CUDA_ARRAY3D_DEPTH_TEXTUREEnum values:
CUDA_ARRAY3D_LAYERED- If set, the CUDA array is a collection of layers, where each layer is either a 1D or a 2D array and the Depth member ofCUDA_ARRAY3D_DESCRIPTORspecifies the number of layers, not the depth of a 3D array.CUDA_ARRAY3D_2DARRAY- Deprecated, useCUDA_ARRAY3D_LAYERED.CUDA_ARRAY3D_SURFACE_LDST- This flag must be set in order to bind a surface reference to the CUDA array.CUDA_ARRAY3D_CUBEMAP- If set, the CUDA array is a collection of six 2D arrays, representing faces of a cube. The width of such a CUDA array must be equal to its height, and Depth must be six. IfCUDA_ARRAY3D_LAYEREDflag is also set, then the CUDA array is a collection of cubemaps and Depth must be a multiple of six.CUDA_ARRAY3D_TEXTURE_GATHER- This flag must be set in order to perform texture gather operations on a CUDA array.CUDA_ARRAY3D_DEPTH_TEXTURE- This flag if set indicates that the CUDA array is a DEPTH_TEXTURE.CUDA_ARRAY3D_COLOR_ATTACHMENT- This flag indicates that the CUDA array may be bound as a color target in an external graphics API.CUDA_ARRAY3D_SPARSE- This flag if set indicates that the CUDA array or CUDA mipmapped array is a sparse CUDA array or CUDA mipmapped array respectively
- See Also:
-
CUDA_ARRAY3D_COLOR_ATTACHMENT
public static final int CUDA_ARRAY3D_COLOR_ATTACHMENTEnum values:
CUDA_ARRAY3D_LAYERED- If set, the CUDA array is a collection of layers, where each layer is either a 1D or a 2D array and the Depth member ofCUDA_ARRAY3D_DESCRIPTORspecifies the number of layers, not the depth of a 3D array.CUDA_ARRAY3D_2DARRAY- Deprecated, useCUDA_ARRAY3D_LAYERED.CUDA_ARRAY3D_SURFACE_LDST- This flag must be set in order to bind a surface reference to the CUDA array.CUDA_ARRAY3D_CUBEMAP- If set, the CUDA array is a collection of six 2D arrays, representing faces of a cube. The width of such a CUDA array must be equal to its height, and Depth must be six. IfCUDA_ARRAY3D_LAYEREDflag is also set, then the CUDA array is a collection of cubemaps and Depth must be a multiple of six.CUDA_ARRAY3D_TEXTURE_GATHER- This flag must be set in order to perform texture gather operations on a CUDA array.CUDA_ARRAY3D_DEPTH_TEXTURE- This flag if set indicates that the CUDA array is a DEPTH_TEXTURE.CUDA_ARRAY3D_COLOR_ATTACHMENT- This flag indicates that the CUDA array may be bound as a color target in an external graphics API.CUDA_ARRAY3D_SPARSE- This flag if set indicates that the CUDA array or CUDA mipmapped array is a sparse CUDA array or CUDA mipmapped array respectively
- See Also:
-
CUDA_ARRAY3D_SPARSE
public static final int CUDA_ARRAY3D_SPARSEEnum values:
CUDA_ARRAY3D_LAYERED- If set, the CUDA array is a collection of layers, where each layer is either a 1D or a 2D array and the Depth member ofCUDA_ARRAY3D_DESCRIPTORspecifies the number of layers, not the depth of a 3D array.CUDA_ARRAY3D_2DARRAY- Deprecated, useCUDA_ARRAY3D_LAYERED.CUDA_ARRAY3D_SURFACE_LDST- This flag must be set in order to bind a surface reference to the CUDA array.CUDA_ARRAY3D_CUBEMAP- If set, the CUDA array is a collection of six 2D arrays, representing faces of a cube. The width of such a CUDA array must be equal to its height, and Depth must be six. IfCUDA_ARRAY3D_LAYEREDflag is also set, then the CUDA array is a collection of cubemaps and Depth must be a multiple of six.CUDA_ARRAY3D_TEXTURE_GATHER- This flag must be set in order to perform texture gather operations on a CUDA array.CUDA_ARRAY3D_DEPTH_TEXTURE- This flag if set indicates that the CUDA array is a DEPTH_TEXTURE.CUDA_ARRAY3D_COLOR_ATTACHMENT- This flag indicates that the CUDA array may be bound as a color target in an external graphics API.CUDA_ARRAY3D_SPARSE- This flag if set indicates that the CUDA array or CUDA mipmapped array is a sparse CUDA array or CUDA mipmapped array respectively
- See Also:
-
CU_TRSA_OVERRIDE_FORMAT
public static final int CU_TRSA_OVERRIDE_FORMATFlag forTexRefSetArray.Enum values:
TRSA_OVERRIDE_FORMAT- Override thetexrefformat with a format inferred from the array.
- See Also:
-
CU_TRSF_READ_AS_INTEGER
public static final int CU_TRSF_READ_AS_INTEGERFlag forTexRefSetFlags.Enum values:
TRSF_READ_AS_INTEGER- Read the texture as integers rather than promoting the values to floats in the range[0,1].TRSF_NORMALIZED_COORDINATES- Use normalized texture coordinates in the range[0,1)instead of[0,dim).TRSF_SRGB- PerformsRGB->linearconversion during texture read.TRSF_DISABLE_TRILINEAR_OPTIMIZATION- Disable any trilinear filtering optimizations.
- See Also:
-
CU_TRSF_NORMALIZED_COORDINATES
public static final int CU_TRSF_NORMALIZED_COORDINATESFlag forTexRefSetFlags.Enum values:
TRSF_READ_AS_INTEGER- Read the texture as integers rather than promoting the values to floats in the range[0,1].TRSF_NORMALIZED_COORDINATES- Use normalized texture coordinates in the range[0,1)instead of[0,dim).TRSF_SRGB- PerformsRGB->linearconversion during texture read.TRSF_DISABLE_TRILINEAR_OPTIMIZATION- Disable any trilinear filtering optimizations.
- See Also:
-
CU_TRSF_SRGB
public static final int CU_TRSF_SRGBFlag forTexRefSetFlags.Enum values:
TRSF_READ_AS_INTEGER- Read the texture as integers rather than promoting the values to floats in the range[0,1].TRSF_NORMALIZED_COORDINATES- Use normalized texture coordinates in the range[0,1)instead of[0,dim).TRSF_SRGB- PerformsRGB->linearconversion during texture read.TRSF_DISABLE_TRILINEAR_OPTIMIZATION- Disable any trilinear filtering optimizations.
- See Also:
-
CU_TRSF_DISABLE_TRILINEAR_OPTIMIZATION
public static final int CU_TRSF_DISABLE_TRILINEAR_OPTIMIZATIONFlag forTexRefSetFlags.Enum values:
TRSF_READ_AS_INTEGER- Read the texture as integers rather than promoting the values to floats in the range[0,1].TRSF_NORMALIZED_COORDINATES- Use normalized texture coordinates in the range[0,1)instead of[0,dim).TRSF_SRGB- PerformsRGB->linearconversion during texture read.TRSF_DISABLE_TRILINEAR_OPTIMIZATION- Disable any trilinear filtering optimizations.
- See Also:
-
CU_LAUNCH_PARAM_END
public static final long CU_LAUNCH_PARAM_ENDEnd of array terminator for theextraparameter toLaunchKernel.- See Also:
-
CU_LAUNCH_PARAM_BUFFER_POINTER
public static final long CU_LAUNCH_PARAM_BUFFER_POINTERIndicator that the next value in theextraparameter toLaunchKernelwill be a pointer to a buffer containing all kernel parameters used for launching kernelf.This buffer needs to honor all alignment/padding requirements of the individual parameters. If
LAUNCH_PARAM_BUFFER_SIZEis not also specified in theextraarray, thenLAUNCH_PARAM_BUFFER_POINTERwill have no effect.- See Also:
-
CU_LAUNCH_PARAM_BUFFER_SIZE
public static final long CU_LAUNCH_PARAM_BUFFER_SIZEIndicator that the next value in theextraparameter toLaunchKernelwill be a pointer to asize_twhich contains the size of the buffer specified withLAUNCH_PARAM_BUFFER_POINTER.It is required that
CU_LAUNCH_PARAM_BUFFER_POINTERalso be specified in theextraarray if the value associated withCU_LAUNCH_PARAM_BUFFER_SIZEis not zero.- See Also:
-
CU_PARAM_TR_DEFAULT
public static final int CU_PARAM_TR_DEFAULTFor texture references loaded into the module, use default texunit from texture reference.- See Also:
-
CU_DEVICE_CPU
public static final int CU_DEVICE_CPUDevice that represents the CPU.- See Also:
-
CU_DEVICE_INVALID
public static final int CU_DEVICE_INVALIDDevice that represents an invalid device.- See Also:
-
CU_FLUSH_GPU_DIRECT_RDMA_WRITES_OPTION_HOST
public static final int CU_FLUSH_GPU_DIRECT_RDMA_WRITES_OPTION_HOSTBitmasks forDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS. (CUflushGPUDirectRDMAWritesOptions)Enum values:
FLUSH_GPU_DIRECT_RDMA_WRITES_OPTION_HOST-FlushGPUDirectRDMAWritesand its CUDA Runtime API counterpart are supported on the device.FLUSH_GPU_DIRECT_RDMA_WRITES_OPTION_MEMOPS- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOpare supported on the device.
- See Also:
-
CU_FLUSH_GPU_DIRECT_RDMA_WRITES_OPTION_MEMOPS
public static final int CU_FLUSH_GPU_DIRECT_RDMA_WRITES_OPTION_MEMOPSBitmasks forDEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS. (CUflushGPUDirectRDMAWritesOptions)Enum values:
FLUSH_GPU_DIRECT_RDMA_WRITES_OPTION_HOST-FlushGPUDirectRDMAWritesand its CUDA Runtime API counterpart are supported on the device.FLUSH_GPU_DIRECT_RDMA_WRITES_OPTION_MEMOPS- TheSTREAM_WAIT_VALUE_FLUSHflag and theSTREAM_MEM_OP_FLUSH_REMOTE_WRITESMemOpare supported on the device.
- See Also:
-
CU_GPU_DIRECT_RDMA_WRITES_ORDERING_NONE
public static final int CU_GPU_DIRECT_RDMA_WRITES_ORDERING_NONEPlatform native ordering for GPUDirect RDMA writes. (CUGPUDirectRDMAWritesOrdering)Enum values:
GPU_DIRECT_RDMA_WRITES_ORDERING_NONE- The device does not natively support ordering of remote writes.FlushGPUDirectRDMAWritescan be leveraged if supported.GPU_DIRECT_RDMA_WRITES_ORDERING_OWNER- Natively, the device can consistently consume remote writes, although other CUDA devices may not.GPU_DIRECT_RDMA_WRITES_ORDERING_ALL_DEVICES- Any CUDA device in the system can consistently consume remote writes to this device.
- See Also:
-
CU_GPU_DIRECT_RDMA_WRITES_ORDERING_OWNER
public static final int CU_GPU_DIRECT_RDMA_WRITES_ORDERING_OWNERPlatform native ordering for GPUDirect RDMA writes. (CUGPUDirectRDMAWritesOrdering)Enum values:
GPU_DIRECT_RDMA_WRITES_ORDERING_NONE- The device does not natively support ordering of remote writes.FlushGPUDirectRDMAWritescan be leveraged if supported.GPU_DIRECT_RDMA_WRITES_ORDERING_OWNER- Natively, the device can consistently consume remote writes, although other CUDA devices may not.GPU_DIRECT_RDMA_WRITES_ORDERING_ALL_DEVICES- Any CUDA device in the system can consistently consume remote writes to this device.
- See Also:
-
CU_GPU_DIRECT_RDMA_WRITES_ORDERING_ALL_DEVICES
public static final int CU_GPU_DIRECT_RDMA_WRITES_ORDERING_ALL_DEVICESPlatform native ordering for GPUDirect RDMA writes. (CUGPUDirectRDMAWritesOrdering)Enum values:
GPU_DIRECT_RDMA_WRITES_ORDERING_NONE- The device does not natively support ordering of remote writes.FlushGPUDirectRDMAWritescan be leveraged if supported.GPU_DIRECT_RDMA_WRITES_ORDERING_OWNER- Natively, the device can consistently consume remote writes, although other CUDA devices may not.GPU_DIRECT_RDMA_WRITES_ORDERING_ALL_DEVICES- Any CUDA device in the system can consistently consume remote writes to this device.
- See Also:
-
CU_FLUSH_GPU_DIRECT_RDMA_WRITES_TO_OWNER
public static final int CU_FLUSH_GPU_DIRECT_RDMA_WRITES_TO_OWNERThe scopes forFlushGPUDirectRDMAWrites(CUflushGPUDirectRDMAWritesScope)Enum values:
FLUSH_GPU_DIRECT_RDMA_WRITES_TO_OWNER- Blocks until remote writes are visible to the CUDA device context owning the data.FLUSH_GPU_DIRECT_RDMA_WRITES_TO_ALL_DEVICES- Blocks until remote writes are visible to all CUDA device contexts.
- See Also:
-
CU_FLUSH_GPU_DIRECT_RDMA_WRITES_TO_ALL_DEVICES
public static final int CU_FLUSH_GPU_DIRECT_RDMA_WRITES_TO_ALL_DEVICESThe scopes forFlushGPUDirectRDMAWrites(CUflushGPUDirectRDMAWritesScope)Enum values:
FLUSH_GPU_DIRECT_RDMA_WRITES_TO_OWNER- Blocks until remote writes are visible to the CUDA device context owning the data.FLUSH_GPU_DIRECT_RDMA_WRITES_TO_ALL_DEVICES- Blocks until remote writes are visible to all CUDA device contexts.
- See Also:
-
CU_FLUSH_GPU_DIRECT_RDMA_WRITES_TARGET_CURRENT_CTX
public static final int CU_FLUSH_GPU_DIRECT_RDMA_WRITES_TARGET_CURRENT_CTXThe targets forFlushGPUDirectRDMAWrites(CUflushGPUDirectRDMAWritesTarget)Enum values:
FLUSH_GPU_DIRECT_RDMA_WRITES_TARGET_CURRENT_CTX- Sets the target forcuFlushGPUDirectRDMAWrites()to the currently active CUDA device context.
- See Also:
-
CU_GRAPH_DEBUG_DOT_FLAGS_VERBOSE
public static final int CU_GRAPH_DEBUG_DOT_FLAGS_VERBOSEThe additional write options forGraphDebugDotPrint(CUgraphDebugDot_flags)Enum values:
GRAPH_DEBUG_DOT_FLAGS_VERBOSEGRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES- Output all debug data as if every debug flag is enabledGRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS- Use CUDA Runtime structures for outputGRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS- AddsCUDA_KERNEL_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS- AddsCUDA_MEMCPY3Dvalues to outputGRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS- AddsCUDA_MEMSET_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS- AddsCUDA_HOST_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS- AddsCUeventhandle from record and wait nodes to outputGRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS- AddsCUDA_EXT_SEM_SIGNAL_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES- AddsCUDA_EXT_SEM_WAIT_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_HANDLES- AddsCUkernelNodeAttrValuevalues to outputGRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS- Adds node handles and every kernel function handle to outputGRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS- Adds memory alloc node parameters to output
- See Also:
-
CU_GRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES
public static final int CU_GRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPESThe additional write options forGraphDebugDotPrint(CUgraphDebugDot_flags)Enum values:
GRAPH_DEBUG_DOT_FLAGS_VERBOSEGRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES- Output all debug data as if every debug flag is enabledGRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS- Use CUDA Runtime structures for outputGRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS- AddsCUDA_KERNEL_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS- AddsCUDA_MEMCPY3Dvalues to outputGRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS- AddsCUDA_MEMSET_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS- AddsCUDA_HOST_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS- AddsCUeventhandle from record and wait nodes to outputGRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS- AddsCUDA_EXT_SEM_SIGNAL_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES- AddsCUDA_EXT_SEM_WAIT_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_HANDLES- AddsCUkernelNodeAttrValuevalues to outputGRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS- Adds node handles and every kernel function handle to outputGRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS- Adds memory alloc node parameters to output
- See Also:
-
CU_GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS
public static final int CU_GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMSThe additional write options forGraphDebugDotPrint(CUgraphDebugDot_flags)Enum values:
GRAPH_DEBUG_DOT_FLAGS_VERBOSEGRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES- Output all debug data as if every debug flag is enabledGRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS- Use CUDA Runtime structures for outputGRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS- AddsCUDA_KERNEL_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS- AddsCUDA_MEMCPY3Dvalues to outputGRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS- AddsCUDA_MEMSET_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS- AddsCUDA_HOST_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS- AddsCUeventhandle from record and wait nodes to outputGRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS- AddsCUDA_EXT_SEM_SIGNAL_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES- AddsCUDA_EXT_SEM_WAIT_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_HANDLES- AddsCUkernelNodeAttrValuevalues to outputGRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS- Adds node handles and every kernel function handle to outputGRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS- Adds memory alloc node parameters to output
- See Also:
-
CU_GRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS
public static final int CU_GRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMSThe additional write options forGraphDebugDotPrint(CUgraphDebugDot_flags)Enum values:
GRAPH_DEBUG_DOT_FLAGS_VERBOSEGRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES- Output all debug data as if every debug flag is enabledGRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS- Use CUDA Runtime structures for outputGRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS- AddsCUDA_KERNEL_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS- AddsCUDA_MEMCPY3Dvalues to outputGRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS- AddsCUDA_MEMSET_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS- AddsCUDA_HOST_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS- AddsCUeventhandle from record and wait nodes to outputGRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS- AddsCUDA_EXT_SEM_SIGNAL_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES- AddsCUDA_EXT_SEM_WAIT_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_HANDLES- AddsCUkernelNodeAttrValuevalues to outputGRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS- Adds node handles and every kernel function handle to outputGRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS- Adds memory alloc node parameters to output
- See Also:
-
CU_GRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS
public static final int CU_GRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMSThe additional write options forGraphDebugDotPrint(CUgraphDebugDot_flags)Enum values:
GRAPH_DEBUG_DOT_FLAGS_VERBOSEGRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES- Output all debug data as if every debug flag is enabledGRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS- Use CUDA Runtime structures for outputGRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS- AddsCUDA_KERNEL_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS- AddsCUDA_MEMCPY3Dvalues to outputGRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS- AddsCUDA_MEMSET_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS- AddsCUDA_HOST_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS- AddsCUeventhandle from record and wait nodes to outputGRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS- AddsCUDA_EXT_SEM_SIGNAL_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES- AddsCUDA_EXT_SEM_WAIT_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_HANDLES- AddsCUkernelNodeAttrValuevalues to outputGRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS- Adds node handles and every kernel function handle to outputGRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS- Adds memory alloc node parameters to output
- See Also:
-
CU_GRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS
public static final int CU_GRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMSThe additional write options forGraphDebugDotPrint(CUgraphDebugDot_flags)Enum values:
GRAPH_DEBUG_DOT_FLAGS_VERBOSEGRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES- Output all debug data as if every debug flag is enabledGRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS- Use CUDA Runtime structures for outputGRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS- AddsCUDA_KERNEL_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS- AddsCUDA_MEMCPY3Dvalues to outputGRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS- AddsCUDA_MEMSET_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS- AddsCUDA_HOST_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS- AddsCUeventhandle from record and wait nodes to outputGRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS- AddsCUDA_EXT_SEM_SIGNAL_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES- AddsCUDA_EXT_SEM_WAIT_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_HANDLES- AddsCUkernelNodeAttrValuevalues to outputGRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS- Adds node handles and every kernel function handle to outputGRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS- Adds memory alloc node parameters to output
- See Also:
-
CU_GRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS
public static final int CU_GRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMSThe additional write options forGraphDebugDotPrint(CUgraphDebugDot_flags)Enum values:
GRAPH_DEBUG_DOT_FLAGS_VERBOSEGRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES- Output all debug data as if every debug flag is enabledGRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS- Use CUDA Runtime structures for outputGRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS- AddsCUDA_KERNEL_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS- AddsCUDA_MEMCPY3Dvalues to outputGRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS- AddsCUDA_MEMSET_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS- AddsCUDA_HOST_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS- AddsCUeventhandle from record and wait nodes to outputGRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS- AddsCUDA_EXT_SEM_SIGNAL_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES- AddsCUDA_EXT_SEM_WAIT_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_HANDLES- AddsCUkernelNodeAttrValuevalues to outputGRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS- Adds node handles and every kernel function handle to outputGRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS- Adds memory alloc node parameters to output
- See Also:
-
CU_GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS
public static final int CU_GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMSThe additional write options forGraphDebugDotPrint(CUgraphDebugDot_flags)Enum values:
GRAPH_DEBUG_DOT_FLAGS_VERBOSEGRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES- Output all debug data as if every debug flag is enabledGRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS- Use CUDA Runtime structures for outputGRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS- AddsCUDA_KERNEL_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS- AddsCUDA_MEMCPY3Dvalues to outputGRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS- AddsCUDA_MEMSET_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS- AddsCUDA_HOST_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS- AddsCUeventhandle from record and wait nodes to outputGRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS- AddsCUDA_EXT_SEM_SIGNAL_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES- AddsCUDA_EXT_SEM_WAIT_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_HANDLES- AddsCUkernelNodeAttrValuevalues to outputGRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS- Adds node handles and every kernel function handle to outputGRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS- Adds memory alloc node parameters to output
- See Also:
-
CU_GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS
public static final int CU_GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMSThe additional write options forGraphDebugDotPrint(CUgraphDebugDot_flags)Enum values:
GRAPH_DEBUG_DOT_FLAGS_VERBOSEGRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES- Output all debug data as if every debug flag is enabledGRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS- Use CUDA Runtime structures for outputGRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS- AddsCUDA_KERNEL_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS- AddsCUDA_MEMCPY3Dvalues to outputGRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS- AddsCUDA_MEMSET_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS- AddsCUDA_HOST_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS- AddsCUeventhandle from record and wait nodes to outputGRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS- AddsCUDA_EXT_SEM_SIGNAL_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES- AddsCUDA_EXT_SEM_WAIT_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_HANDLES- AddsCUkernelNodeAttrValuevalues to outputGRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS- Adds node handles and every kernel function handle to outputGRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS- Adds memory alloc node parameters to output
- See Also:
-
CU_GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES
public static final int CU_GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTESThe additional write options forGraphDebugDotPrint(CUgraphDebugDot_flags)Enum values:
GRAPH_DEBUG_DOT_FLAGS_VERBOSEGRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES- Output all debug data as if every debug flag is enabledGRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS- Use CUDA Runtime structures for outputGRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS- AddsCUDA_KERNEL_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS- AddsCUDA_MEMCPY3Dvalues to outputGRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS- AddsCUDA_MEMSET_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS- AddsCUDA_HOST_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS- AddsCUeventhandle from record and wait nodes to outputGRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS- AddsCUDA_EXT_SEM_SIGNAL_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES- AddsCUDA_EXT_SEM_WAIT_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_HANDLES- AddsCUkernelNodeAttrValuevalues to outputGRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS- Adds node handles and every kernel function handle to outputGRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS- Adds memory alloc node parameters to output
- See Also:
-
CU_GRAPH_DEBUG_DOT_FLAGS_HANDLES
public static final int CU_GRAPH_DEBUG_DOT_FLAGS_HANDLESThe additional write options forGraphDebugDotPrint(CUgraphDebugDot_flags)Enum values:
GRAPH_DEBUG_DOT_FLAGS_VERBOSEGRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES- Output all debug data as if every debug flag is enabledGRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS- Use CUDA Runtime structures for outputGRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS- AddsCUDA_KERNEL_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS- AddsCUDA_MEMCPY3Dvalues to outputGRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS- AddsCUDA_MEMSET_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS- AddsCUDA_HOST_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS- AddsCUeventhandle from record and wait nodes to outputGRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS- AddsCUDA_EXT_SEM_SIGNAL_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES- AddsCUDA_EXT_SEM_WAIT_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_HANDLES- AddsCUkernelNodeAttrValuevalues to outputGRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS- Adds node handles and every kernel function handle to outputGRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS- Adds memory alloc node parameters to output
- See Also:
-
CU_GRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS
public static final int CU_GRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMSThe additional write options forGraphDebugDotPrint(CUgraphDebugDot_flags)Enum values:
GRAPH_DEBUG_DOT_FLAGS_VERBOSEGRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES- Output all debug data as if every debug flag is enabledGRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS- Use CUDA Runtime structures for outputGRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS- AddsCUDA_KERNEL_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS- AddsCUDA_MEMCPY3Dvalues to outputGRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS- AddsCUDA_MEMSET_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS- AddsCUDA_HOST_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS- AddsCUeventhandle from record and wait nodes to outputGRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS- AddsCUDA_EXT_SEM_SIGNAL_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES- AddsCUDA_EXT_SEM_WAIT_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_HANDLES- AddsCUkernelNodeAttrValuevalues to outputGRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS- Adds node handles and every kernel function handle to outputGRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS- Adds memory alloc node parameters to output
- See Also:
-
CU_GRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS
public static final int CU_GRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMSThe additional write options forGraphDebugDotPrint(CUgraphDebugDot_flags)Enum values:
GRAPH_DEBUG_DOT_FLAGS_VERBOSEGRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES- Output all debug data as if every debug flag is enabledGRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS- Use CUDA Runtime structures for outputGRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS- AddsCUDA_KERNEL_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS- AddsCUDA_MEMCPY3Dvalues to outputGRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS- AddsCUDA_MEMSET_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS- AddsCUDA_HOST_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS- AddsCUeventhandle from record and wait nodes to outputGRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS- AddsCUDA_EXT_SEM_SIGNAL_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES- AddsCUDA_EXT_SEM_WAIT_NODE_PARAMSvalues to outputGRAPH_DEBUG_DOT_FLAGS_HANDLES- AddsCUkernelNodeAttrValuevalues to outputGRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS- Adds node handles and every kernel function handle to outputGRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS- Adds memory alloc node parameters to output
- See Also:
-
CU_USER_OBJECT_NO_DESTRUCTOR_SYNC
public static final int CU_USER_OBJECT_NO_DESTRUCTOR_SYNCFlags for user objects for graphs. (CUuserObject_flags)Enum values:
USER_OBJECT_NO_DESTRUCTOR_SYNC- Indicates the destructor execution is not synchronized by any CUDA handle.
- See Also:
-
CU_GRAPH_USER_OBJECT_MOVE
public static final int CU_GRAPH_USER_OBJECT_MOVEFlags for retaining user object references for graphs. (CUuserObjectRetain_flags)Enum values:
GRAPH_USER_OBJECT_MOVE- Transfer references from the caller rather than creating new references.
- See Also:
-
CUDA_GRAPH_INSTANTIATE_FLAG_AUTO_FREE_ON_LAUNCH
public static final int CUDA_GRAPH_INSTANTIATE_FLAG_AUTO_FREE_ON_LAUNCHFlags for instantiating a graph. (CUgraphInstantiate_flags)Enum values:
CUDA_GRAPH_INSTANTIATE_FLAG_AUTO_FREE_ON_LAUNCH- Automatically free memory allocated in a graph before relaunching.
- See Also:
-
-
Method Details
-
getLibrary
Returns the NVCUDASharedLibrary. -
ncuGetErrorString
public static int ncuGetErrorString(int error, long pStr) Unsafe version of:GetErrorString -
cuGetErrorString
Gets the string description of an error code.Sets
*pStrto the address of a NULL-terminated string description of the error codeerror. If the error code is not recognized,CUDA_ERROR_INVALID_VALUEwill be returned and*pStrwill be set to theNULLaddress.- Parameters:
error- error code to convert to stringpStr- address of the string pointer
-
ncuGetErrorName
public static int ncuGetErrorName(int error, long pStr) Unsafe version of:GetErrorName -
cuGetErrorName
Gets the string representation of an error code enum name.Sets
*pStrto the address of a NULL-terminated string representation of the name of the enum error codeerror. If the error code is not recognized,CUDA_ERROR_INVALID_VALUEwill be returned and*pStrwill be set to theNULLaddress.- Parameters:
error- error code to convert to stringpStr- address of the string pointer
-
cuInit
public static int cuInit(int Flags) Initialize the CUDA driver API.Initializes the driver API and must be called before any other function from the driver API. Currently, the
Flagsparameter must be 0. IfcuInit()has not been called, any function from the driver API will returnCUDA_ERROR_NOT_INITIALIZED.- Parameters:
Flags- initialization flag for CUDA
-
ncuDriverGetVersion
public static int ncuDriverGetVersion(long driverVersion) Unsafe version of:DriverGetVersion -
cuDriverGetVersion
Returns the latest CUDA version supported by driver.Returns in
*driverVersionthe version of CUDA supported by the driver. The version is returned as (1000 × major + 10 × minor). For example, CUDA 9.2 would be represented by 9020.This function automatically returns
CUDA_ERROR_INVALID_VALUEifdriverVersionisNULL.- Parameters:
driverVersion- returns the CUDA driver version
-
ncuDeviceGet
public static int ncuDeviceGet(long device, int ordinal) Unsafe version of:DeviceGet -
cuDeviceGet
Returns a handle to a compute device.Returns in
*devicea device handle given an ordinal in the range[0, cuDeviceGetCount()-1].- Parameters:
device- returned device handleordinal- device number to get handle for
-
ncuDeviceGetCount
public static int ncuDeviceGetCount(long count) Unsafe version of:DeviceGetCount -
cuDeviceGetCount
Returns the number of compute-capable devices.Returns in
*countthe number of devices with compute capability greater than or equal to 2.0 that are available for execution. If there is no such device,cuDeviceGetCount()returns 0.- Parameters:
count- returned number of compute-capable devices
-
ncuDeviceGetName
public static int ncuDeviceGetName(long name, int len, int dev) Unsafe version of:DeviceGetName- Parameters:
len- maximum length of string to store inname
-
cuDeviceGetName
Returns an identifer string for the device.Returns an ASCII string identifying the device
devin the NULL-terminated string pointed to byname.lenspecifies the maximum length of the string that may be returned.- Parameters:
name- returned identifier string for the devicedev- device to get identifier string for
-
ncuDeviceGetUuid
public static int ncuDeviceGetUuid(long uuid, int dev) Unsafe version of:DeviceGetUuid -
cuDeviceGetUuid
Return an UUID for the device.Note there is a later version of this API,
DeviceGetUuid_v2. It will supplant this version in 12.0, which is retained for minor version. compatibility.Returns 16-octets identifing the device
devin the structure pointed by theuuid.- Parameters:
uuid- returned UUIDdev- device to get identifier string for
-
ncuDeviceGetUuid_v2
public static int ncuDeviceGetUuid_v2(long uuid, int dev) Unsafe version of:DeviceGetUuid_v2 -
cuDeviceGetUuid_v2
Return an UUID for the device (11.4+).Returns 16-octets identifing the device
devin the structure pointed by theuuid. If the device is in MIG mode, returns its MIG UUID which uniquely identifies the subscribed MIG compute instance.- Parameters:
uuid- returned UUIDdev- device to get identifier string for
-
ncuDeviceGetLuid
public static int ncuDeviceGetLuid(long luid, long deviceNodeMask, int dev) Unsafe version of:DeviceGetLuid -
cuDeviceGetLuid
Return an LUID and device node mask for the deviceReturn identifying information (
luidanddeviceNodeMask) to allow matching device with graphics APIs.- Parameters:
luid- returned LUIDdeviceNodeMask- returned device node maskdev- device to get identifier string for
-
ncuDeviceTotalMem
public static int ncuDeviceTotalMem(long bytes, int dev) Unsafe version of:DeviceTotalMem -
cuDeviceTotalMem
Returns the total amount of memory on the deviceReturns in
*bytesthe total amount of memory available on the devicedevin bytes.- Parameters:
bytes- returned memory available on device in bytesdev- device handle
-
ncuDeviceGetTexture1DLinearMaxWidth
public static int ncuDeviceGetTexture1DLinearMaxWidth(long maxWidthInElements, int format, int numChannels, int dev) Unsafe version of:DeviceGetTexture1DLinearMaxWidth -
cuDeviceGetTexture1DLinearMaxWidth
public static int cuDeviceGetTexture1DLinearMaxWidth(PointerBuffer maxWidthInElements, int format, int numChannels, int dev) Returns the maximum number of elements allocatable in a 1D linear texture for a given texture element size.Returns in
maxWidthInElementsthe maximum number of texture elements allocatable in a 1D linear texture for givenformatandnumChannels.- Parameters:
maxWidthInElements- returned maximum number of texture elements allocatable for givenformatandnumChannelsformat- texture formatnumChannels- number of channels per texture elementdev- device handle
-
ncuDeviceGetAttribute
public static int ncuDeviceGetAttribute(long pi, int attrib, int dev) Unsafe version of:DeviceGetAttribute -
cuDeviceGetAttribute
Returns information about the device.Returns in
*pithe integer value of the attributeattribon devicedev. The supported attributes are:- Parameters:
pi- returned device attribute valueattrib- device attribute to querydev- device handle
-
ncuDeviceGetNvSciSyncAttributes
public static int ncuDeviceGetNvSciSyncAttributes(long nvSciSyncAttrList, int dev, int flags) Unsafe version of:DeviceGetNvSciSyncAttributes -
cuDeviceGetNvSciSyncAttributes
ReturnNvSciSyncattributes that this device can support.Returns in
nvSciSyncAttrList, the properties ofNvSciSyncthat this CUDA device,devcan support. The returnednvSciSyncAttrListcan be used to create anNvSciSyncobject that matches this device's capabilities.If
NvSciSyncAttrKey_RequiredPermfield innvSciSyncAttrListis already set this API will returnCUDA_ERROR_INVALID_VALUE.The applications should set
nvSciSyncAttrListto a validNvSciSyncAttrListfailing which this API will returnCUDA_ERROR_INVALID_HANDLE.The
flagscontrols how applications intends to use theNvSciSynccreated from thenvSciSyncAttrList. The valid flags are:CUDA_NVSCISYNC_ATTR_SIGNAL, specifies that the applications intends to signal anNvSciSyncon this CUDA device.CUDA_NVSCISYNC_ATTR_WAIT, specifies that the applications intends to wait on anNvSciSyncon this CUDA device.
At least one of these flags must be set, failing which the API returns
CUDA_ERROR_INVALID_VALUE. Both the flags are orthogonal to one another: a developer may set both these flags that allows to set both wait and signal specific attributes in the samenvSciSyncAttrList.- Parameters:
nvSciSyncAttrList- return NvSciSync attributes supporteddev- valid Cuda Device to getNvSciSyncattributes forflags- flags describingNvSciSyncusage
-
cuDeviceSetMemPool
public static int cuDeviceSetMemPool(int dev, long pool) Sets the current memory pool of a deviceThe memory pool must be local to the specified device.
MemAllocAsyncallocates from the current mempool of the provided stream's device. By default, a device's current memory pool is its default memory pool.Note
Use
MemAllocFromPoolAsyncto specify asynchronous allocations from a device different than the one the stream runs on. -
ncuDeviceGetMemPool
public static int ncuDeviceGetMemPool(long pool, int dev) Unsafe version of:DeviceGetMemPool -
cuDeviceGetMemPool
Gets the current mempool for a device.Returns the last pool provided to
DeviceSetMemPoolfor this device or the device's default memory pool ifDeviceSetMemPoolhas never been called. By default the current mempool is the default mempool for a device. Otherwise the returned pool must have been set withDeviceSetMemPool. -
ncuDeviceGetDefaultMemPool
public static int ncuDeviceGetDefaultMemPool(long pool_out, int dev) Unsafe version of:DeviceGetDefaultMemPool -
cuDeviceGetDefaultMemPool
Returns the default mempool of a device.The default mempool of a device contains device memory from that device.
-
cuFlushGPUDirectRDMAWrites
public static int cuFlushGPUDirectRDMAWrites(int target, int scope) Blocks until remote writes are visible to the specified scope.Blocks until GPUDirect RDMA writes to the target context via mappings created through APIs like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information), are visible to the specified scope.
If the scope equals or lies within the scope indicated by
DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING, the call will be a no-op and can be safely omitted for performance. This can be determined by comparing the numerical values between the two enums, with smaller scopes having smaller values.Users may query support for this API via
DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS.- Parameters:
target- the target of the operation, seeCUflushGPUDirectRDMAWritesTargetscope- the scope of the operation, seeCUflushGPUDirectRDMAWritesScope
-
ncuDeviceGetProperties
public static int ncuDeviceGetProperties(long prop, int dev) Unsafe version of:DeviceGetProperties -
cuDeviceGetProperties
Returns properties for a selected device.Deprecated: This function was deprecated as of CUDA 5.0 and replaced by
DeviceGetAttribute.Returns in
*propthe properties of devicedev.- Parameters:
prop- returned properties of devicedev- device to get properties for
-
ncuDeviceComputeCapability
public static int ncuDeviceComputeCapability(long major, long minor, int dev) Unsafe version of:DeviceComputeCapability -
cuDeviceComputeCapability
Returns the compute capability of the device.Deprecated: This function was deprecated as of CUDA 5.0 and its functionality superceded by
DeviceGetAttribute.Returns in
*majorand*minorthe major and minor revision numbers that define the compute capability of the devicedev.- Parameters:
major- major revision numberminor- minor revision numberdev- device handle
-
ncuDevicePrimaryCtxRetain
public static int ncuDevicePrimaryCtxRetain(long pctx, int dev) Unsafe version of:DevicePrimaryCtxRetain -
cuDevicePrimaryCtxRetain
Retain the primary context on the GPU.Retains the primary context on the device. Once the user successfully retains the primary context, the primary context will be active and available to the user until the user releases it with
DevicePrimaryCtxReleaseor resets it withDevicePrimaryCtxReset. UnlikeCtxCreatethe newly retained context is not pushed onto the stack.Retaining the primary context for the first time will fail with
CUDA_ERROR_UNKNOWNif the compute mode of the device isCOMPUTEMODE_PROHIBITED. The functionDeviceGetAttributecan be used withDEVICE_ATTRIBUTE_COMPUTE_MODEto determine the compute mode of the device. The nvidia-smi tool can be used to set the compute mode for devices. Documentation for nvidia-smi can be obtained by passing a -h option to it.Please note that the primary context always supports pinned allocations. Other flags can be specified by
DevicePrimaryCtxSetFlags.- Parameters:
pctx- returned context handle of the new contextdev- device for which primary context is requested
-
cuDevicePrimaryCtxRelease
public static int cuDevicePrimaryCtxRelease(int dev) Release the primary context on the GPU.Releases the primary context interop on the device. A retained context should always be released once the user is done using it. The context is automatically reset once the last reference to it is released. This behavior is different when the primary context was retained by the CUDA runtime from CUDA 4.0 and earlier. In this case, the primary context remains always active.
Releasing a primary context that has not been previously retained will fail with
CUDA_ERROR_INVALID_CONTEXT.Please note that unlike
CtxDestroythis method does not pop the context from stack in any circumstances.- Parameters:
dev- device which primary context is released
-
cuDevicePrimaryCtxSetFlags
public static int cuDevicePrimaryCtxSetFlags(int dev, int flags) Set flags for the primary context.Sets the flags for the primary context on the device overwriting perviously set ones.
The three LSBs of the
flagsparameter can be used to control how the OS thread, which owns the CUDA context at the time of an API call, interacts with the OS scheduler when waiting for results from the GPU. Only one of the scheduling flags can be set when creating a context:CTX_SCHED_SPIN: Instruct CUDA to actively spin when waiting for results from the GPU. This can decrease latency when waiting for the GPU, but may lower the performance of CPU threads if they are performing work in parallel with the CUDA thread.CTX_SCHED_YIELD: Instruct CUDA to yield its thread when waiting for results from the GPU. This can increase latency when waiting for the GPU, but can increase the performance of CPU threads performing work in parallel with the GPU.CTX_SCHED_BLOCKING_SYNC: Instruct CUDA to block the CPU thread on a synchronization primitive when waiting for the GPU to finish work.CTX_BLOCKING_SYNC: Instruct CUDA to block the CPU thread on a synchronization primitive when waiting for the GPU to finish work.Deprecated: This flag was deprecated as of CUDA 4.0 and was replaced with
CTX_SCHED_BLOCKING_SYNC.CTX_SCHED_AUTO: The default value if theflagsparameter is zero, uses a heuristic based on the number of active CUDA contexts in the process C and the number of logical processors in the system P. If C > P, then CUDA will yield to other OS threads when waiting for the GPU (CTX_SCHED_YIELD), otherwise CUDA will not yield while waiting for results and actively spin on the processor (CTX_SCHED_SPIN). Additionally, on Tegra devices,CTX_SCHED_AUTOuses a heuristic based on the power profile of the platform and may chooseCTX_SCHED_BLOCKING_SYNCfor low-powered devices.CTX_LMEM_RESIZE_TO_MAX: Instruct CUDA to not reduce local memory after resizing local memory for a kernel. This can prevent thrashing by local memory allocations when launching many kernels with high local memory usage at the cost of potentially increased memory usage.Deprecated: This flag is deprecated and the behavior enabled by this flag is now the default and cannot be disabled.
- Parameters:
dev- device for which the primary context flags are setflags- new flags for the device
-
ncuDevicePrimaryCtxGetState
public static int ncuDevicePrimaryCtxGetState(int dev, long flags, long active) Unsafe version of:DevicePrimaryCtxGetState -
cuDevicePrimaryCtxGetState
Get the state of the primary context.Returns in
*flagsthe flags for the primary context ofdev, and in*activewhether it is active. SeeDevicePrimaryCtxSetFlagsfor flag values.- Parameters:
dev- device to get primary context flags forflags- pointer to store flagsactive- pointer to store context state; 0 = inactive, 1 = active
-
cuDevicePrimaryCtxReset
public static int cuDevicePrimaryCtxReset(int dev) Destroy all allocations and reset all state on the primary context.Explicitly destroys and cleans up all resources associated with the current device in the current process.
Note that it is responsibility of the calling function to ensure that no other module in the process is using the device any more. For that reason it is recommended to use
DevicePrimaryCtxReleasein most cases. However it is safe for other modules to callcuDevicePrimaryCtxRelease()even after resetting the device. Resetting the primary context does not release it, an application that has retained the primary context should explicitly release its usage.- Parameters:
dev- device for which primary context is destroyed
-
ncuDeviceGetExecAffinitySupport
public static int ncuDeviceGetExecAffinitySupport(long pi, int type, int dev) Unsafe version of:DeviceGetExecAffinitySupport -
cuDeviceGetExecAffinitySupport
Returns information about the execution affinity support of the device.Returns in
*piwhether execution affinity typetypeis supported by devicedev. The supported types are:EXEC_AFFINITY_TYPE_SM_COUNT: 1 if context with limited SMs is supported by the device, or 0 if not;
- Parameters:
pi- 1 if the execution affinity typetypeis supported by the device, or 0 if nottype- execution affinity type to querydev- device handle
-
ncuCtxCreate
public static int ncuCtxCreate(long pctx, int flags, int dev) Unsafe version of:CtxCreate -
cuCtxCreate
Create a CUDA context.Note
In most cases it is recommended to use
DevicePrimaryCtxRetain.Creates a new CUDA context and associates it with the calling thread. The
flagsparameter is described below. The context is created with a usage count of 1 and the caller ofcuCtxCreate()must callCtxDestroyor when done using the context. If a context is already current to the thread, it is supplanted by the newly created context and may be restored by a subsequent call toCtxPopCurrent.The three LSBs of the
flagsparameter can be used to control how the OS thread, which owns the CUDA context at the time of an API call, interacts with the OS scheduler when waiting for results from the GPU. Only one of the scheduling flags can be set when creating a context:CTX_SCHED_SPIN: Instruct CUDA to actively spin when waiting for results from the GPU. This can decrease latency when waiting for the GPU, but may lower the performance of CPU threads if they are performing work in parallel with the CUDA thread.CTX_SCHED_YIELD: Instruct CUDA to yield its thread when waiting for results from the GPU. This can increase latency when waiting for the GPU, but can increase the performance of CPU threads performing work in parallel with the GPU.CTX_SCHED_BLOCKING_SYNC: Instruct CUDA to block the CPU thread on a synchronization primitive when waiting for the GPU to finish work.CTX_BLOCKING_SYNC: Instruct CUDA to block the CPU thread on a synchronization primitive when waiting for the GPU to finish work.Deprecated: This flag was deprecated as of CUDA 4.0 and was replaced with
CTX_SCHED_BLOCKING_SYNC.CTX_SCHED_AUTO: The default value if theflagsparameter is zero, uses a heuristic based on the number of active CUDA contexts in the process C and the number of logical processors in the system P. If C > P, then CUDA will yield to other OS threads when waiting for the GPU (CTX_SCHED_YIELD), otherwise CUDA will not yield while waiting for results and actively spin on the processor (CTX_SCHED_SPIN). Additionally, on Tegra devices,CTX_SCHED_AUTOuses a heuristic based on the power profile of the platform and may chooseCTX_SCHED_BLOCKING_SYNCfor low-powered devices.CTX_MAP_HOST: Instruct CUDA to support mapped pinned allocations. This flag must be set in order to allocate pinned host memory that is accessible to the GPU.CTX_LMEM_RESIZE_TO_MAX: Instruct CUDA to not reduce local memory after resizing local memory for a kernel. This can prevent thrashing by local memory allocations when launching many kernels with high local memory usage at the cost of potentially increased memory usage.Deprecated: This flag is deprecated and the behavior enabled by this flag is now the default and cannot be disabled. Instead, the per-thread stack size can be controlled with
CtxSetLimit.
Context creation will fail with
CUDA_ERROR_UNKNOWNif the compute mode of the device isCOMPUTEMODE_PROHIBITED. The functionDeviceGetAttributecan be used withDEVICE_ATTRIBUTE_COMPUTE_MODEto determine the compute mode of the device. The nvidia-smi tool can be used to set the compute mode for * devices. Documentation for nvidia-smi can be obtained by passing a -h option to it.- Parameters:
pctx- returned context handle of the new contextflags- context creation flagsdev- device to create context on
-
ncuCtxCreate_v3
public static int ncuCtxCreate_v3(long pctx, long paramsArray, int numParams, int flags, int dev) Unsafe version of:CtxCreate_v3- Parameters:
numParams- number of execution affinity parameters
-
cuCtxCreate_v3
public static int cuCtxCreate_v3(PointerBuffer pctx, CUexecAffinityParam.Buffer paramsArray, int flags, int dev) Create a CUDA context with execution affinity.Creates a new CUDA context with execution affinity and associates it with the calling thread. The
paramsArrayandflagsparameter are described below. The context is created with a usage count of 1 and the caller ofCtxCreatemust callCtxDestroyor when done using the context. If a context is already current to the thread, it is supplanted by the newly created context and may be restored by a subsequent call toCtxPopCurrent.The type and the amount of execution resource the context can use is limited by
paramsArrayandnumParams. TheparamsArrayis an array ofCUexecAffinityParamand thenumParamsdescribes the size of the array. If twoCUexecAffinityParamin the array have the same type, the latter execution affinity parameter overrides the former execution affinity parameter. The supported execution affinity types are:EXEC_AFFINITY_TYPE_SM_COUNTlimits the portion of SMs that the context can use. The portion of SMs is specified as the number of SMs viaCUexecAffinitySmCount. This limit will be internally rounded up to the next hardware-supported amount. Hence, it is imperative to query the actual execution affinity of the context viaCtxGetExecAffinity) after context creation. Currently, this attribute is only supported under Volta+ MPS.
The three LSBs of the
flagsparameter can be used to control how the OS thread, which owns the CUDA context at the time of an API call, interacts with the OS scheduler when waiting for results from the GPU. Only one of the scheduling flags can be set when creating a context:CTX_SCHED_SPIN: Instruct CUDA to actively spin when waiting for results from the GPU. This can decrease latency when waiting for the GPU, but may lower the performance of CPU threads if they are performing work in parallel with the CUDA thread.CTX_SCHED_YIELD: Instruct CUDA to yield its thread when waiting for results from the GPU. This can increase latency when waiting for the GPU, but can increase the performance of CPU threads performing work in parallel with the GPU.CTX_SCHED_BLOCKING_SYNC: Instruct CUDA to block the CPU thread on a synchronization primitive when waiting for the GPU to finish work.CTX_BLOCKING_SYNC: Instruct CUDA to block the CPU thread on a synchronization primitive when waiting for the GPU to finish work.Deprecated: This flag was deprecated as of CUDA 4.0 and was replaced with
CTX_SCHED_BLOCKING_SYNC.CTX_SCHED_AUTO: The default value if theflagsparameter is zero, uses a heuristic based on the number of active CUDA contexts in the process C and the number of logical processors in the system P. If C > P, then CUDA will yield to other OS threads when waiting for the GPU (CTX_SCHED_YIELD), otherwise CUDA will not yield while waiting for results and actively spin on the processor (CTX_SCHED_SPIN). Additionally, on Tegra devices,CTX_SCHED_AUTOuses a heuristic based on the power profile of the platform and may chooseCTX_SCHED_BLOCKING_SYNCfor low-powered devices.CTX_MAP_HOST: Instruct CUDA to support mapped pinned allocations. This flag must be set in order to allocate pinned host memory that is accessible to the GPU.CTX_LMEM_RESIZE_TO_MAX: Instruct CUDA to not reduce local memory after resizing local memory for a kernel. This can prevent thrashing by local memory allocations when launching many kernels with high local memory usage at the cost of potentially increased memory usage.Deprecated: This flag is deprecated and the behavior enabled by this flag is now the default and cannot be disabled. Instead, the per-thread stack size can be controlled with
CtxSetLimit.
Context creation will fail with
CUDA_ERROR_UNKNOWNif the compute mode of the device isCOMPUTEMODE_PROHIBITED. The functionDeviceGetAttributecan be used withDEVICE_ATTRIBUTE_COMPUTE_MODEto determine the compute mode of the device. The nvidia-smi tool can be used to set the compute mode for * devices. Documentation for nvidia-smi can be obtained by passing a -h option to it.- Parameters:
pctx- returned context handle of the new contextparamsArray- execution affinity parametersflags- context creation flagsdev- device to create context on
-
cuCtxDestroy
public static int cuCtxDestroy(long ctx) Destroy a CUDA context.Destroys the CUDA context specified by
ctx. The contextctxwill be destroyed regardless of how many threads it is current to. It is the responsibility of the calling function to ensure that no API call issues usingctxwhilecuCtxDestroy()is executing.Destroys and cleans up all resources associated with the context. It is the caller's responsibility to ensure that the context or its resources are not accessed or passed in subsequent API calls and doing so will result in undefined behavior. These resources include CUDA types such as
CUmodule,CUfunction,CUstream,CUevent,CUarray,CUmipmappedArray,CUtexObject,CUsurfObject,CUtexref,CUsurfref,CUgraphicsResource,CUlinkState,CUexternalMemoryandCUexternalSemaphore.If
ctxis current to the calling thread thenctxwill also be popped from the current thread's context stack (as thoughCtxPopCurrentwere called). Ifctxis current to other threads, thenctxwill remain current to those threads, and attempting to accessctxfrom those threads will result in the errorCUDA_ERROR_CONTEXT_IS_DESTROYED.- Parameters:
ctx- context to destroy
-
cuCtxPushCurrent
public static int cuCtxPushCurrent(long ctx) Pushes a context on the current CPU thread.Pushes the given context
ctxonto the CPU thread's stack of current contexts. The specified context becomes the CPU thread's current context, so all CUDA functions that operate on the current context are affected.The previous current context may be made current again by calling
CtxDestroyorCtxPopCurrent.- Parameters:
ctx- context to push
-
ncuCtxPopCurrent
public static int ncuCtxPopCurrent(long pctx) Unsafe version of:CtxPopCurrent -
cuCtxPopCurrent
Pops the current CUDA context from the current CPU thread.Pops the current CUDA context from the CPU thread and passes back the old context handle in
*pctx. That context may then be made current to a different CPU thread by callingCtxPushCurrent.If a context was current to the CPU thread before
CtxCreateorCtxPushCurrentwas called, this function makes that context current to the CPU thread again.- Parameters:
pctx- returned new context handle
-
cuCtxSetCurrent
public static int cuCtxSetCurrent(long ctx) Binds the specified CUDA context to the calling CPU thread.Binds the specified CUDA context to the calling CPU thread. If
ctxisNULLthen the CUDA context previously bound to the calling CPU thread is unbound andCUDA_SUCCESSis returned.If there exists a CUDA context stack on the calling CPU thread, this will replace the top of that stack with
ctx. IfctxisNULLthen this will be equivalent to popping the top of the calling CPU thread's CUDA context stack (or a no-op if the calling CPU thread's CUDA context stack is empty).- Parameters:
ctx- context to bind to the calling CPU thread
-
ncuCtxGetCurrent
public static int ncuCtxGetCurrent(long pctx) Unsafe version of:CtxGetCurrent -
cuCtxGetCurrent
Returns the CUDA context bound to the calling CPU thread.Returns in
*pctxthe CUDA context bound to the calling CPU thread. If no context is bound to the calling CPU thread then*pctxis set toNULLandCUDA_SUCCESSis returned.- Parameters:
pctx- returned context handle
-
ncuCtxGetDevice
public static int ncuCtxGetDevice(long device) Unsafe version of:CtxGetDevice -
cuCtxGetDevice
Returns the device ID for the current context.Returns in
*devicethe ordinal of the current context's device.- Parameters:
device- returned device ID for the current context
-
ncuCtxGetFlags
public static int ncuCtxGetFlags(long flags) Unsafe version of:CtxGetFlags -
cuCtxGetFlags
Returns the flags for the current context.Returns in
*flagsthe flags of the current context. SeeCtxCreatefor flag values.- Parameters:
flags- pointer to store flags of current context
-
cuCtxSynchronize
public static int cuCtxSynchronize()Block for a context's tasks to complete.Blocks until the device has completed all preceding requested tasks.
cuCtxSynchronize()returns an error if one of the preceding tasks failed. If the context was created with theCTX_SCHED_BLOCKING_SYNCflag, the CPU thread will block until the GPU context has finished its work. -
cuCtxSetLimit
public static int cuCtxSetLimit(int limit, long value) Set resource limits.Setting
limittovalueis a request by the application to update the current limit maintained by the context. The driver is free to modify the requested value to meet h/w requirements (this could be clamping to minimum or maximum values, rounding up to nearest element size, etc). The application can useCtxGetLimitto find out exactly what the limit has been set to.Setting each
CUlimithas its own specific restrictions, so each is discussed here.LIMIT_STACK_SIZEcontrols the stack size in bytes of each GPU thread. The driver automatically increases the per-thread stack size for each kernel launch as needed. This size isn't reset back to the original value after each launch. Setting this value will take effect immediately, and if necessary, the device will block until all preceding requested tasks are complete.LIMIT_PRINTF_FIFO_SIZEcontrols the size in bytes of the FIFO used by theprintf()device system call. SettingLIMIT_PRINTF_FIFO_SIZEmust be performed before launching any kernel that uses theprintf()device system call, otherwiseCUDA_ERROR_INVALID_VALUEwill be returned.LIMIT_MALLOC_HEAP_SIZEcontrols the size in bytes of the heap used by themalloc()andfree()device system calls. SettingCU_LIMIT_MALLOC_HEAP_SIZEmust be performed before launching any kernel that uses themalloc()orfree()device system calls, otherwiseCUDA_ERROR_INVALID_VALUEwill be returned.LIMIT_DEV_RUNTIME_SYNC_DEPTHcontrols the maximum nesting depth of a grid at which a thread can safely callcudaDeviceSynchronize(). Setting this limit must be performed before any launch of a kernel that uses the device runtime and callscudaDeviceSynchronize()above the default sync depth, two levels of grids. Calls tocudaDeviceSynchronize()will fail with error codecudaErrorSyncDepthExceededif the limitation is violated. This limit can be set smaller than the default or up the maximum launch depth of 24. When setting this limit, keep in mind that additional levels of sync depth require the driver to reserve large amounts of device memory which can no longer be used for user allocations. If these reservations of device memory fail,cuCtxSetLimit()will returnCUDA_ERROR_OUT_OF_MEMORY, and the limit can be reset to a lower value. This limit is only applicable to devices of compute capability 3.5 and higher. Attempting to set this limit on devices of compute capability less than 3.5 will result in the errorCUDA_ERROR_UNSUPPORTED_LIMITbeing returned.LIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNTcontrols the maximum number of outstanding device runtime launches that can be made from the current context. A grid is outstanding from the point of launch up until the grid is known to have been completed. Device runtime launches which violate this limitation fail and returncudaErrorLaunchPendingCountExceededwhencudaGetLastError()is called after launch. If more pending launches than the default (2048 launches) are needed for a module using the device runtime, this limit can be increased. Keep in mind that being able to sustain additional pending launches will require the driver to reserve larger amounts of device memory upfront which can no longer be used for allocations. If these reservations fail,cuCtxSetLimit()will returnCUDA_ERROR_OUT_OF_MEMORY, and the limit can be reset to a lower value. This limit is only applicable to devices of compute capability 3.5 and higher. Attempting to set this limit on devices of compute capability less than 3.5 will result in the errorCUDA_ERROR_UNSUPPORTED_LIMITbeing returned.LIMIT_MAX_L2_FETCH_GRANULARITYcontrols the L2 cache fetch granularity. Values can range from 0B to 128B. This is purely a performence hint and it can be ignored or clamped depending on the platform.LIMIT_PERSISTING_L2_CACHE_SIZEcontrols size in bytes availabe for persisting L2 cache. This is purely a performance hint and it can be ignored or clamped depending on the platform.
- Parameters:
limit- limit to setvalue- size of limit
-
ncuCtxGetLimit
public static int ncuCtxGetLimit(long pvalue, int limit) Unsafe version of:CtxGetLimit -
cuCtxGetLimit
Returns resource limits.Returns in
*pvaluethe current size oflimit.- Parameters:
pvalue- returned size of limitlimit- limit to query
-
ncuCtxGetCacheConfig
public static int ncuCtxGetCacheConfig(long pconfig) Unsafe version of:CtxGetCacheConfig -
cuCtxGetCacheConfig
Returns the preferred cache configuration for the current context.On devices where the L1 cache and shared memory use the same hardware resources, this function returns through
pconfigthe preferred cache configuration for the current context. This is only a preference. The driver will use the requested configuration if possible, but it is free to choose a different configuration if required to execute functions.This will return a
pconfigofFUNC_CACHE_PREFER_NONEon devices where the size of the L1 cache and shared memory are fixed.- Parameters:
pconfig- returned cache configuration
-
cuCtxSetCacheConfig
public static int cuCtxSetCacheConfig(int config) Sets the preferred cache configuration for the current context.On devices where the L1 cache and shared memory use the same hardware resources, this sets through
configthe preferred cache configuration for the current context. This is only a preference. The driver will use the requested configuration if possible, but it is free to choose a different configuration if required to execute the function. Any function preference set viacuFuncSetCacheConfig()will be preferred over this context-wide setting. Setting the context-wide cache configuration toFUNC_CACHE_PREFER_NONEwill cause subsequent kernel launches to prefer to not change the cache configuration unless required to launch the kernel.This setting does nothing on devices where the size of the L1 cache and shared memory are fixed.
Launching a kernel with a different preference than the most recent preference setting may insert a device-side synchronization point.
- Parameters:
config- requested cache configuration
-
ncuCtxGetApiVersion
public static int ncuCtxGetApiVersion(long ctx, long version) Unsafe version of:CtxGetApiVersion -
cuCtxGetApiVersion
Gets the context's API version.Returns a version number in
versioncorresponding to the capabilities of the context (e.g. 3010 or 3020), which library developers can use to direct callers to a specific API version. IfctxisNULL, returns the API version used to create the currently bound context.Note that new API versions are only introduced when context capabilities are changed that break binary compatibility, so the API version and driver version may be different. For example, it is valid for the API version to be 3020 while the driver version is 4020.
- Parameters:
ctx- context to checkversion- pointer to version
-
ncuCtxGetStreamPriorityRange
public static int ncuCtxGetStreamPriorityRange(long leastPriority, long greatestPriority) Unsafe version of:CtxGetStreamPriorityRange -
cuCtxGetStreamPriorityRange
public static int cuCtxGetStreamPriorityRange(@Nullable IntBuffer leastPriority, @Nullable IntBuffer greatestPriority) Returns numerical values that correspond to the least and greatest stream priorities.Returns in
*leastPriorityand*greatestPrioritythe numerical values that correspond to the least and greatest stream priorities respectively. Stream priorities follow a convention where lower numbers imply greater priorities. The range of meaningful stream priorities is given by [*greatestPriority,*leastPriority]. If the user attempts to create a stream with a priority value that is outside the meaningful range as specified by this API, the priority is automatically clamped down or up to either*leastPriorityor*greatestPriorityrespectively. SeeStreamCreateWithPriorityfor details on creating a priority stream. ANULLmay be passed in for*leastPriorityorgreatestPriorityif the value is not desired.This function will return
0in both*leastPriorityand*greatestPriorityif the current context's device does not support stream priorities (seeDeviceGetAttribute).- Parameters:
leastPriority- pointer to an int in which the numerical value for least stream priority is returnedgreatestPriority- pointer to an int in which the numerical value for greatest stream priority is returned
-
cuCtxResetPersistingL2Cache
public static int cuCtxResetPersistingL2Cache()Resets all persisting lines in cache to normal status.Takes effect on function return.
-
ncuCtxGetExecAffinity
public static int ncuCtxGetExecAffinity(long pExecAffinity, int type) Unsafe version of:CtxGetExecAffinity -
cuCtxGetExecAffinity
Returns the execution affinity setting for the current context.Returns in
*pExecAffinitythe current value oftype.- Parameters:
pExecAffinity- returned execution affinitytype- execution affinity type to query
-
ncuCtxAttach
public static int ncuCtxAttach(long pctx, int flags) Unsafe version of:CtxAttach -
cuCtxAttach
Increment a context's usage-count.Deprecated: Note that this function is deprecated and should not be used.
Increments the usage count of the context and passes back a context handle in
*pctxthat must be passed toCtxDetachwhen the application is done with the context.cuCtxAttach()fails if there is no context current to the thread.Currently, the
flagsparameter must be 0.- Parameters:
pctx- returned context handle of the current contextflags- context attach flags (must be 0)
-
cuCtxDetach
public static int cuCtxDetach(long ctx) Decrement a context's usage-countDeprecated: Note that this function is deprecated and should not be used.
Decrements the usage count of the context
ctx, and destroys the context if the usage count goes to 0. The context must be a handle that was passed back byCtxCreateorCtxAttach, and must be current to the calling thread.- Parameters:
ctx- context to destroy
-
ncuModuleLoad
public static int ncuModuleLoad(long module, long fname) Unsafe version of:ModuleLoad -
cuModuleLoad
Loads a compute module.Takes a filename
fnameand loads the corresponding modulemoduleinto the current context. The CUDA driver API does not attempt to lazily allocate the resources needed by a module; if the memory for functions and data (constant and global) needed by the module cannot be allocated,cuModuleLoad()fails. The file should be a cubin file as output by nvcc, or a PTX file either as output by nvcc or handwritten, or a fatbin file as output by nvcc from toolchain 4.0 or later.- Parameters:
module- returned modulefname- filename of module to load
-
cuModuleLoad
Loads a compute module.Takes a filename
fnameand loads the corresponding modulemoduleinto the current context. The CUDA driver API does not attempt to lazily allocate the resources needed by a module; if the memory for functions and data (constant and global) needed by the module cannot be allocated,cuModuleLoad()fails. The file should be a cubin file as output by nvcc, or a PTX file either as output by nvcc or handwritten, or a fatbin file as output by nvcc from toolchain 4.0 or later.- Parameters:
module- returned modulefname- filename of module to load
-
ncuModuleLoadData
public static int ncuModuleLoadData(long module, long image) Unsafe version of:ModuleLoadData -
cuModuleLoadData
Load a module's data.Takes a pointer
imageand loads the corresponding modulemoduleinto the current context. The pointer may be obtained by mapping a cubin or PTX or fatbin file, passing a cubin or PTX or fatbin file as a NULL-terminated text string, or incorporating a cubin or fatbin object into the executable resources and using operating system calls such as WindowsFindResource()to obtain the pointer.- Parameters:
module- returned moduleimage- module data to load
-
ncuModuleLoadDataEx
public static int ncuModuleLoadDataEx(long module, long image, int numOptions, long options, long optionValues) Unsafe version of:ModuleLoadDataEx- Parameters:
numOptions- number of options
-
cuModuleLoadDataEx
public static int cuModuleLoadDataEx(PointerBuffer module, ByteBuffer image, @Nullable IntBuffer options, @Nullable PointerBuffer optionValues) Load a module's data with options.Takes a pointer
imageand loads the corresponding modulemoduleinto the current context. The pointer may be obtained by mapping a cubin or PTX or fatbin file, passing a cubin or PTX or fatbin file as a NULL-terminated text string, or incorporating a cubin or fatbin object into the executable resources and using operating system calls such as WindowsFindResource()to obtain the pointer. Options are passed as an array viaoptionsand any corresponding parameters are passed inoptionValues. The number of total options is supplied vianumOptions. Any outputs will be returned viaoptionValues.- Parameters:
module- returned moduleimage- module data to loadoptions- options for JIToptionValues- option values for JIT
-
ncuModuleLoadFatBinary
public static int ncuModuleLoadFatBinary(long module, long fatCubin) Unsafe version of:ModuleLoadFatBinary -
cuModuleLoadFatBinary
Load a module's data.Takes a pointer
fatCubinand loads the corresponding modulemoduleinto the current context. The pointer represents a fat binary object, which is a collection of different cubin and/or PTX files, all representing the same device code, but compiled and optimized for different architectures.Prior to CUDA 4.0, there was no documented API for constructing and using fat binary objects by programmers. Starting with CUDA 4.0, fat binary objects can be constructed by providing the -fatbin option to nvcc. More information can be found in the nvcc document.
- Parameters:
module- returned modulefatCubin- fat binary to load
-
cuModuleUnload
public static int cuModuleUnload(long hmod) Unloads a module.Unloads a module
hmodfrom the current context.- Parameters:
hmod- module to unload
-
ncuModuleGetFunction
public static int ncuModuleGetFunction(long hfunc, long hmod, long name) Unsafe version of:ModuleGetFunction -
cuModuleGetFunction
Returns a function handle.Returns in
*hfuncthe handle of the function of namenamelocated in modulehmod. If no function of that name exists,cuModuleGetFunction()returnsCUDA_ERROR_NOT_FOUND.- Parameters:
hfunc- returned function handlehmod- module to retrieve function fromname- name of function to retrieve
-
cuModuleGetFunction
Returns a function handle.Returns in
*hfuncthe handle of the function of namenamelocated in modulehmod. If no function of that name exists,cuModuleGetFunction()returnsCUDA_ERROR_NOT_FOUND.- Parameters:
hfunc- returned function handlehmod- module to retrieve function fromname- name of function to retrieve
-
ncuModuleGetGlobal
public static int ncuModuleGetGlobal(long dptr, long bytes, long hmod, long name) Unsafe version of:ModuleGetGlobal -
cuModuleGetGlobal
public static int cuModuleGetGlobal(@Nullable PointerBuffer dptr, @Nullable PointerBuffer bytes, long hmod, ByteBuffer name) Returns a global pointer from a module.Returns in
*dptrand*bytesthe base pointer and size of the global of namenamelocated in modulehmod. If no variable of that name exists,cuModuleGetGlobal()returnsCUDA_ERROR_NOT_FOUND. Both parametersdptrandbytesare optional. If one of them isNULL, it is ignored.- Parameters:
dptr- returned global device pointerbytes- returned global size in byteshmod- module to retrieve global fromname- name of global to retrieve
-
cuModuleGetGlobal
public static int cuModuleGetGlobal(@Nullable PointerBuffer dptr, @Nullable PointerBuffer bytes, long hmod, CharSequence name) Returns a global pointer from a module.Returns in
*dptrand*bytesthe base pointer and size of the global of namenamelocated in modulehmod. If no variable of that name exists,cuModuleGetGlobal()returnsCUDA_ERROR_NOT_FOUND. Both parametersdptrandbytesare optional. If one of them isNULL, it is ignored.- Parameters:
dptr- returned global device pointerbytes- returned global size in byteshmod- module to retrieve global fromname- name of global to retrieve
-
ncuModuleGetTexRef
public static int ncuModuleGetTexRef(long pTexRef, long hmod, long name) Unsafe version of:ModuleGetTexRef -
cuModuleGetTexRef
Returns a handle to a texture reference.Returns in
*pTexRefthe handle of the texture reference of namenamein the modulehmod. If no texture reference of that name exists,cuModuleGetTexRef()returnsCUDA_ERROR_NOT_FOUND. This texture reference handle should not be destroyed, since it will be destroyed when the module is unloaded.- Parameters:
pTexRef- returned texture referencehmod- module to retrieve texture reference fromname- name of texture reference to retrieve
-
cuModuleGetTexRef
Returns a handle to a texture reference.Returns in
*pTexRefthe handle of the texture reference of namenamein the modulehmod. If no texture reference of that name exists,cuModuleGetTexRef()returnsCUDA_ERROR_NOT_FOUND. This texture reference handle should not be destroyed, since it will be destroyed when the module is unloaded.- Parameters:
pTexRef- returned texture referencehmod- module to retrieve texture reference fromname- name of texture reference to retrieve
-
ncuModuleGetSurfRef
public static int ncuModuleGetSurfRef(long pSurfRef, long hmod, long name) Unsafe version of:ModuleGetSurfRef -
cuModuleGetSurfRef
Returns a handle to a surface reference.Returns in
*pSurfRefthe handle of the surface reference of namenamein the modulehmod. If no surface reference of that name exists,cuModuleGetSurfRef()returnsCUDA_ERROR_NOT_FOUND.- Parameters:
pSurfRef- returned surface referencehmod- module to retrieve surface reference fromname- name of surface reference to retrieve
-
cuModuleGetSurfRef
Returns a handle to a surface reference.Returns in
*pSurfRefthe handle of the surface reference of namenamein the modulehmod. If no surface reference of that name exists,cuModuleGetSurfRef()returnsCUDA_ERROR_NOT_FOUND.- Parameters:
pSurfRef- returned surface referencehmod- module to retrieve surface reference fromname- name of surface reference to retrieve
-
ncuLinkCreate
public static int ncuLinkCreate(int numOptions, long options, long optionValues, long stateOut) Unsafe version of:LinkCreate- Parameters:
numOptions- size of options arrays
-
cuLinkCreate
public static int cuLinkCreate(IntBuffer options, PointerBuffer optionValues, PointerBuffer stateOut) Creates a pending JIT linker invocation.If the call is successful, the caller owns the returned
CUlinkState, which should eventually be destroyed withLinkDestroy. The device code machine size (32 or 64 bit) will match the calling application.Both linker and compiler options may be specified. Compiler options will be applied to inputs to this linker action which must be compiled from PTX. The options
JIT_WALL_TIME,JIT_INFO_LOG_BUFFER_SIZE_BYTES, andJIT_ERROR_LOG_BUFFER_SIZE_BYTESwill accumulate data until theCUlinkStateis destroyed.optionValuesmust remain valid for the life of theCUlinkStateif output options are used. No other references to inputs are maintained after this call returns.- Parameters:
options- array of linker and compiler optionsoptionValues- array of option values, each cast to void *stateOut- on success, this will contain aCUlinkStateto specify and complete this action
-
ncuLinkAddData
public static int ncuLinkAddData(long state, int type, long data, long size, long name, int numOptions, long options, long optionValues) Unsafe version of:LinkAddData- Parameters:
size- the length of the input datanumOptions- size of options
-
cuLinkAddData
public static int cuLinkAddData(long state, int type, ByteBuffer data, ByteBuffer name, IntBuffer options, PointerBuffer optionValues) Add an input to a pending linker invocation.Ownership of
datais retained by the caller. No reference is retained to any inputs after this call returns.This method accepts only compiler options, which are used if the data must be compiled from PTX, and does not accept any of
JIT_WALL_TIME,JIT_INFO_LOG_BUFFER,JIT_ERROR_LOG_BUFFER,JIT_TARGET_FROM_CUCONTEXT, orJIT_TARGET.- Parameters:
state- a pending linker actiontype- the type of the input datadata- the input data. PTX must be NULL-terminated.name- an optional name for this input in log messagesoptions- options to be applied only for this input (overrides options fromLinkCreate)optionValues- array of option values, each cast to void *
-
cuLinkAddData
public static int cuLinkAddData(long state, int type, ByteBuffer data, CharSequence name, IntBuffer options, PointerBuffer optionValues) Add an input to a pending linker invocation.Ownership of
datais retained by the caller. No reference is retained to any inputs after this call returns.This method accepts only compiler options, which are used if the data must be compiled from PTX, and does not accept any of
JIT_WALL_TIME,JIT_INFO_LOG_BUFFER,JIT_ERROR_LOG_BUFFER,JIT_TARGET_FROM_CUCONTEXT, orJIT_TARGET.- Parameters:
state- a pending linker actiontype- the type of the input datadata- the input data. PTX must be NULL-terminated.name- an optional name for this input in log messagesoptions- options to be applied only for this input (overrides options fromLinkCreate)optionValues- array of option values, each cast to void *
-
ncuLinkAddFile
public static int ncuLinkAddFile(long state, int type, long path, int numOptions, long options, long optionValues) Unsafe version of:LinkAddFile- Parameters:
numOptions- size of options
-
cuLinkAddFile
public static int cuLinkAddFile(long state, int type, ByteBuffer path, IntBuffer options, PointerBuffer optionValues) Add a file input to a pending linker invocation.No reference is retained to any inputs after this call returns.
This method accepts only compiler options, which are used if the input must be compiled from PTX, and does not accept any of
JIT_WALL_TIME,JIT_INFO_LOG_BUFFER,JIT_ERROR_LOG_BUFFER,JIT_TARGET_FROM_CUCONTEXT, orJIT_TARGET.This method is equivalent to invoking
LinkAddDataon the contents of the file.- Parameters:
state- a pending linker actiontype- the type of the input datapath- path to the input fileoptions- options to be applied only for this input (overrides options fromLinkCreate)optionValues- array of option values, each cast to void *
-
cuLinkAddFile
public static int cuLinkAddFile(long state, int type, CharSequence path, IntBuffer options, PointerBuffer optionValues) Add a file input to a pending linker invocation.No reference is retained to any inputs after this call returns.
This method accepts only compiler options, which are used if the input must be compiled from PTX, and does not accept any of
JIT_WALL_TIME,JIT_INFO_LOG_BUFFER,JIT_ERROR_LOG_BUFFER,JIT_TARGET_FROM_CUCONTEXT, orJIT_TARGET.This method is equivalent to invoking
LinkAddDataon the contents of the file.- Parameters:
state- a pending linker actiontype- the type of the input datapath- path to the input fileoptions- options to be applied only for this input (overrides options fromLinkCreate)optionValues- array of option values, each cast to void *
-
ncuLinkComplete
public static int ncuLinkComplete(long state, long cubinOut, long sizeOut) Unsafe version of:LinkComplete -
cuLinkComplete
Complete a pending linker invocation.Completes the pending linker action and returns the cubin image for the linked device code, which can be used with
ModuleLoadData. The cubin is owned bystate, so it should be loaded beforestateis destroyed viaLinkDestroy. This call does not destroystate.- Parameters:
state- a pending linker invocationcubinOut- on success, this will point to the output imagesizeOut- optional parameter to receive the size of the generated image
-
cuLinkDestroy
public static int cuLinkDestroy(long state) Destroys state for a JIT linker invocation.- Parameters:
state- state object for the linker invocation
-
ncuMemGetInfo
public static int ncuMemGetInfo(long free, long total) Unsafe version of:MemGetInfo -
cuMemGetInfo
Gets free and total memory.Returns in
*totalthe total amount of memory available to the the current context. Returns in*freethe amount of memory on the device that is free according to the OS. CUDA is not guaranteed to be able to allocate all of the memory that the OS reports as free.- Parameters:
free- returned free memory in bytestotal- returned total memory in bytes
-
ncuMemAlloc
public static int ncuMemAlloc(long dptr, long bytesize) Unsafe version of:MemAlloc -
cuMemAlloc
Allocates device memory.Allocates
bytesizebytes of linear memory on the device and returns in*dptra pointer to the allocated memory. The allocated memory is suitably aligned for any kind of variable. The memory is not cleared. Ifbytesizeis 0,cuMemAlloc()returnsCUDA_ERROR_INVALID_VALUE.- Parameters:
dptr- returned device pointerbytesize- requested allocation size in bytes
-
ncuMemAllocPitch
public static int ncuMemAllocPitch(long dptr, long pPitch, long WidthInBytes, long Height, int ElementSizeBytes) Unsafe version of:MemAllocPitch -
cuMemAllocPitch
public static int cuMemAllocPitch(PointerBuffer dptr, PointerBuffer pPitch, long WidthInBytes, long Height, int ElementSizeBytes) Allocates pitched device memory.Allocates at least
WidthInBytes*Heightbytes of linear memory on the device and returns in*dptra pointer to the allocated memory. The function may pad the allocation to ensure that corresponding pointers in any given row will continue to meet the alignment requirements for coalescing as the address is updated from row to row.ElementSizeBytesspecifies the size of the largest reads and writes that will be performed on the memory range.ElementSizeBytesmay be 4, 8 or 16 (since coalesced memory transactions are not possible on other data sizes). IfElementSizeBytesis smaller than the actual read/write size of a kernel, the kernel will run correctly, but possibly at reduced speed. The pitch returned in*pPitchbycuMemAllocPitch()is the width in bytes of the allocation. The intended usage of pitch is as a separate parameter of the allocation, used to compute addresses within the 2D array. Given the row and column of an array element of type T, the address is computed as:T* pElement = (T*)((char*)BaseAddress + Row * Pitch) + Column;The pitch returned by
cuMemAllocPitch()is guaranteed to work withMemcpy2Dunder all circumstances. For allocations of 2D arrays, it is recommended that programmers consider performing pitch allocations usingcuMemAllocPitch(). Due to alignment restrictions in the hardware, this is especially true if the application will be performing 2D memory copies between different regions of device memory (whether linear memory or CUDA arrays).The byte alignment of the pitch returned by
cuMemAllocPitch()is guaranteed to match or exceed the alignment requirement for texture binding withTexRefSetAddress2D.- Parameters:
dptr- returned device pointerpPitch- returned pitch of allocation in bytesWidthInBytes- requested allocation width in bytesHeight- requested allocation height in rowsElementSizeBytes- size of largest reads/writes for range
-
cuMemFree
public static int cuMemFree(long dptr) Frees device memory.Frees the memory space pointed to by
dptr, which must have been returned by a previous call toMemAllocorMemAllocPitch.- Parameters:
dptr- pointer to memory to free
-
ncuMemGetAddressRange
public static int ncuMemGetAddressRange(long pbase, long psize, long dptr) Unsafe version of:MemGetAddressRange -
cuMemGetAddressRange
public static int cuMemGetAddressRange(@Nullable PointerBuffer pbase, @Nullable PointerBuffer psize, long dptr) Get information on memory allocations.Returns the base address in
*pbaseand size in*psizeof the allocation byMemAllocorMemAllocPitchthat contains the input pointerdptr. Both parameterspbaseandpsizeare optional. If one of them isNULL, it is ignored.- Parameters:
pbase- returned base addresspsize- returned size of device memory allocationdptr- device pointer to query
-
ncuMemAllocHost
public static int ncuMemAllocHost(long pp, long bytesize) Unsafe version of:MemAllocHost -
cuMemAllocHost
Allocates page-locked host memory.Allocates
bytesizebytes of host memory that is page-locked and accessible to the device. The driver tracks the virtual memory ranges allocated with this function and automatically accelerates calls to functions such asMemcpy. Since the memory can be accessed directly by the device, it can be read or written with much higher bandwidth than pageable memory obtained with functions such asmalloc(). Allocating excessive amounts of memory withcuMemAllocHost()may degrade system performance, since it reduces the amount of memory available to the system for paging. As a result, this function is best used sparingly to allocate staging areas for data exchange between host and device.Note all host memory allocated using
cuMemHostAlloc()will automatically be immediately accessible to all contexts on all devices which support unified addressing (as may be queried usingDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING). The device pointer that may be used to access this host memory from those contexts is always equal to the returned host pointer*pp. SeeCUDA_UNIFIEDfor additional details.- Parameters:
pp- returned host pointer to page-locked memorybytesize- requested allocation size in bytes
-
ncuMemFreeHost
public static int ncuMemFreeHost(long p) Unsafe version of:MemFreeHost -
cuMemFreeHost
Frees page-locked host memory.Frees the memory space pointed to by
p, which must have been returned by a previous call toMemAllocHost.- Parameters:
p- pointer to memory to free
-
ncuMemHostAlloc
public static int ncuMemHostAlloc(long pp, long bytesize, int Flags) Unsafe version of:MemHostAlloc -
cuMemHostAlloc
Allocates page-locked host memory.Allocates
bytesizebytes of host memory that is page-locked and accessible to the device. The driver tracks the virtual memory ranges allocated with this function and automatically accelerates calls to functions such asMemcpyHtoD. Since the memory can be accessed directly by the device, it can be read or written with much higher bandwidth than pageable memory obtained with functions such asmalloc(). Allocating excessive amounts of pinned memory may degrade system performance, since it reduces the amount of memory available to the system for paging. As a result, this function is best used sparingly to allocate staging areas for data exchange between host and device.The
Flagsparameter enables different options to be specified that affect the allocation, as follows:MEMHOSTALLOC_PORTABLE: The memory returned by this call will be considered as pinned memory by all CUDA contexts, not just the one that performed the allocation.MEMHOSTALLOC_DEVICEMAP: Maps the allocation into the CUDA address space. The device pointer to the memory may be obtained by callingMemHostGetDevicePointer.MEMHOSTALLOC_WRITECOMBINED: Allocates the memory as write-combined (WC). WC memory can be transferred across the PCI Express bus more quickly on some system configurations, but cannot be read efficiently by most CPUs. WC memory is a good option for buffers that will be written by the CPU and read by the GPU via mapped pinned memory or host->device transfers.
All of these flags are orthogonal to one another: a developer may allocate memory that is portable, mapped and/or write-combined with no restrictions.
The
MEMHOSTALLOC_DEVICEMAPflag may be specified on CUDA contexts for devices that do not support mapped pinned memory. The failure is deferred toMemHostGetDevicePointerbecause the memory may be mapped into other CUDA contexts via theMEMHOSTALLOC_PORTABLEflag.The memory allocated by this function must be freed with
MemFreeHost.Note all host memory allocated using
cuMemHostAlloc()will automatically be immediately accessible to all contexts on all devices which support unified addressing (as may be queried usingDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING). Unless the flagMEMHOSTALLOC_WRITECOMBINEDis specified, the device pointer that may be used to access this host memory from those contexts is always equal to the returned host pointer*pp. If the flagMEMHOSTALLOC_WRITECOMBINEDis specified, then the functionMemHostGetDevicePointermust be used to query the device pointer, even if the context supports unified addressing. SeeCUDA_UNIFIEDfor additional details.- Parameters:
pp- returned host pointer to page-locked memorybytesize- requested allocation size in bytesFlags- flags for allocation request
-
ncuMemHostGetDevicePointer
public static int ncuMemHostGetDevicePointer(long pdptr, long p, int Flags) Unsafe version of:MemHostGetDevicePointer -
cuMemHostGetDevicePointer
Passes back device pointer of mapped pinned memory.Passes back the device pointer
pdptrcorresponding to the mapped, pinned host bufferpallocated byMemHostAlloc.cuMemHostGetDevicePointer()will fail if theMEMHOSTALLOC_DEVICEMAPflag was not specified at the time the memory was allocated, or if the function is called on a GPU that does not support mapped pinned memory.For devices that have a non-zero value for the device attribute
DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM, the memory can also be accessed from the device using the host pointerp. The device pointer returned bycuMemHostGetDevicePointer()may or may not match the original host pointerpand depends on the devices visible to the application. If all devices visible to the application have a non-zero value for the device attribute, the device pointer returned bycuMemHostGetDevicePointer()will match the original pointerp. If any device visible to the application has a zero value for the device attribute, the device pointer returned bycuMemHostGetDevicePointer()will not match the original host pointerp, but it will be suitable for use on all devices provided Unified Virtual Addressing is enabled. In such systems, it is valid to access the memory using either pointer on devices that have a non-zero value for the device attribute. Note however that such devices should access the memory using only of the two pointers and not both.Flagsprovides for future releases. For now, it must be set to 0.- Parameters:
pdptr- returned device pointerp- host pointerFlags- options (must be 0)
-
ncuMemHostGetFlags
public static int ncuMemHostGetFlags(long pFlags, long p) Unsafe version of:MemHostGetFlags -
cuMemHostGetFlags
Passes back flags that were used for a pinned allocationPasses back the flags
pFlagsthat were specified when allocating the pinned host bufferpallocated byMemHostAlloc.cuMemHostGetFlags()will fail if the pointer does not reside in an allocation performed byMemAllocHostorcuMemHostAlloc().- Parameters:
pFlags- returned flags wordp- host pointer
-
ncuMemAllocManaged
public static int ncuMemAllocManaged(long dptr, long bytesize, int flags) Unsafe version of:MemAllocManaged -
cuMemAllocManaged
Allocates memory that will be automatically managed by the Unified Memory system.Allocates
bytesizebytes of managed memory on the device and returns in*dptra pointer to the allocated memory. If the device doesn't support allocating managed memory,CUDA_ERROR_NOT_SUPPORTEDis returned. Support for managed memory can be queried using the device attributeDEVICE_ATTRIBUTE_MANAGED_MEMORY. The allocated memory is suitably aligned for any kind of variable. The memory is not cleared. Ifbytesizeis 0,MemAllocManagedreturnsCUDA_ERROR_INVALID_VALUE. The pointer is valid on the CPU and on all GPUs in the system that support managed memory. All accesses to this pointer must obey the Unified Memory programming model.flagsspecifies the default stream association for this allocation.flagsmust be one ofMEM_ATTACH_GLOBALorMEM_ATTACH_HOST. IfMEM_ATTACH_GLOBALis specified, then this memory is accessible from any stream on any device. IfMEM_ATTACH_HOSTis specified, then the allocation should not be accessed from devices that have a zero value for the device attributeDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS; an explicit call toStreamAttachMemAsyncwill be required to enable access on such devices.If the association is later changed via
StreamAttachMemAsyncto a single stream, the default association as specifed duringMemAllocManagedis restored when that stream is destroyed. For __managed__ variables, the default association is alwaysMEM_ATTACH_GLOBAL. Note that destroying a stream is an asynchronous operation, and as a result, the change to default association won't happen until all work in the stream has completed.Memory allocated with
MemAllocManagedshould be released withMemFree.Device memory oversubscription is possible for GPUs that have a non-zero value for the device attribute
DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS. Managed memory on such GPUs may be evicted from device memory to host memory at any time by the Unified Memory driver in order to make room for other allocations.In a multi-GPU system where all GPUs have a non-zero value for the device attribute
DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS, managed memory may not be populated when this API returns and instead may be populated on access. In such systems, managed memory can migrate to any processor's memory at any time. The Unified Memory driver will employ heuristics to maintain data locality and prevent excessive page faults to the extent possible. The application can also guide the driver about memory usage patterns viaMemAdvise. The application can also explicitly migrate memory to a desired processor's memory viaMemPrefetchAsync.In a multi-GPU system where all of the GPUs have a zero value for the device attribute
DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESSand all the GPUs have peer-to-peer support with each other, the physical storage for managed memory is created on the GPU which is active at the timeMemAllocManagedis called. All other GPUs will reference the data at reduced bandwidth via peer mappings over the PCIe bus. The Unified Memory driver does not migrate memory among such GPUs.In a multi-GPU system where not all GPUs have peer-to-peer support with each other and where the value of the device attribute
DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESSis zero for at least one of those GPUs, the location chosen for physical storage of managed memory is system-dependent.- On Linux, the location chosen will be device memory as long as the current set of active contexts are on devices that either have peer-to-peer
support with each other or have a non-zero value for the device attribute
DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS. If there is an active context on a GPU that does not have a non-zero value for that device attribute and it does not have peer-to-peer support with the other devices that have active contexts on them, then the location for physical storage will be 'zero-copy' or host memory. Note that this means that managed memory that is located in device memory is migrated to host memory if a new context is created on a GPU that doesn't have a non-zero value for the device attribute and does not support peer-to-peer with at least one of the other devices that has an active context. This in turn implies that context creation may fail if there is insufficient host memory to migrate all managed allocations. - On Windows, the physical storage is always created in 'zero-copy' or host memory. All GPUs will reference the data at reduced bandwidth over the
PCIe bus. In these circumstances, use of the environment variable
CUDA_VISIBLE_DEVICESis recommended to restrict CUDA to only use those GPUs that have peer-to-peer support. Alternatively, users can also setCUDA_MANAGED_FORCE_DEVICE_ALLOCto a non-zero value to force the driver to always use device memory for physical storage. When this environment variable is set to a non-zero value, all contexts created in that process on devices that support managed memory have to be peer-to-peer compatible with each other. Context creation will fail if a context is created on a device that supports managed memory and is not peer-to-peer compatible with any of the other managed memory supporting devices on which contexts were previously created, even if those contexts have been destroyed. These environment variables are described in the CUDA programming guide under the "CUDA environment variables" section. - On ARM, managed memory is not available on discrete gpu with Drive PX-2.
- Parameters:
dptr- returned device pointerbytesize- requested allocation size in bytesflags- must be one ofMEM_ATTACH_GLOBALorMEM_ATTACH_HOST
- On Linux, the location chosen will be device memory as long as the current set of active contexts are on devices that either have peer-to-peer
support with each other or have a non-zero value for the device attribute
-
ncuDeviceGetByPCIBusId
public static int ncuDeviceGetByPCIBusId(long dev, long pciBusId) Unsafe version of:DeviceGetByPCIBusId -
cuDeviceGetByPCIBusId
Returns a handle to a compute device.Returns in
*devicea device handle given a PCI bus ID string.- Parameters:
dev- returned device handlepciBusId- string in one of the following forms:[domain]:[bus]:[device].[function] [domain]:[bus]:[device] [bus]:[device].[function]wheredomain,bus,device, andfunctionare all hexadecimal values
-
cuDeviceGetByPCIBusId
Returns a handle to a compute device.Returns in
*devicea device handle given a PCI bus ID string.- Parameters:
dev- returned device handlepciBusId- string in one of the following forms:[domain]:[bus]:[device].[function] [domain]:[bus]:[device] [bus]:[device].[function]wheredomain,bus,device, andfunctionare all hexadecimal values
-
ncuDeviceGetPCIBusId
public static int ncuDeviceGetPCIBusId(long pciBusId, int len, int dev) Unsafe version of:DeviceGetPCIBusId- Parameters:
len- maximum length of string to store inname
-
cuDeviceGetPCIBusId
Returns a PCI Bus Id string for the device.Returns an ASCII string identifying the device
devin the NULL-terminated string pointed to bypciBusId.lenspecifies the maximum length of the string that may be returned.- Parameters:
pciBusId- returned identifier string for the device in the following format[domain]:[bus]:[device].[function]wheredomain,bus,device, andfunctionare all hexadecimal values.pciBusIdshould be large enough to store 13 characters including the NULL-terminator.dev- device to get identifier string for
-
ncuIpcGetEventHandle
public static int ncuIpcGetEventHandle(long pHandle, long event) Unsafe version of:IpcGetEventHandle -
cuIpcGetEventHandle
Gets an interprocess handle for a previously allocated event.Takes as input a previously allocated event. This event must have been created with the
EVENT_INTERPROCESSandEVENT_DISABLE_TIMINGflags set. This opaque handle may be copied into other processes and opened withIpcOpenEventHandleto allow efficient hardware synchronization between GPU work in different processes.After the event has been opened in the importing process,
EventRecord,EventSynchronize,StreamWaitEventandEventQuerymay be used in either process. Performing operations on the imported event after the exported event has been freed withEventDestroywill result in undefined behavior.IPC functionality is restricted to devices with support for unified addressing on Linux and Windows operating systems. IPC functionality on Windows is restricted to GPUs in TCC mode.
- Parameters:
pHandle- pointer to a user allocatedCUipcEventHandlein which to return the opaque event handleevent- event allocated withEVENT_INTERPROCESSandEVENT_DISABLE_TIMINGflags
-
ncuIpcOpenEventHandle
public static int ncuIpcOpenEventHandle(long phEvent, long handle) Unsafe version of:IpcOpenEventHandle -
cuIpcOpenEventHandle
Opens an interprocess event handle for use in the current process.Opens an interprocess event handle exported from another process with
IpcGetEventHandle. This function returns aCUeventthat behaves like a locally created event with theEVENT_DISABLE_TIMINGflag specified. This event must be freed withEventDestroy.Performing operations on the imported event after the exported event has been freed with
cuEventDestroywill result in undefined behavior.IPC functionality is restricted to devices with support for unified addressing on Linux and Windows operating systems. IPC functionality on Windows is restricted to GPUs in TCC mode.
- Parameters:
phEvent- returns the imported eventhandle- interprocess handle to open
-
ncuIpcGetMemHandle
public static int ncuIpcGetMemHandle(long pHandle, long dptr) Unsafe version of:IpcGetMemHandle -
cuIpcGetMemHandle
Gets an interprocess memory handle for an existing device memory allocation.Takes a pointer to the base of an existing device memory allocation created with
MemAllocand exports it for use in another process. This is a lightweight operation and may be called multiple times on an allocation without adverse effects.If a region of memory is freed with
MemFreeand a subsequent call toMemAllocreturns memory with the same device address,IpcGetMemHandlewill return a unique handle for the new memory.IPC functionality is restricted to devices with support for unified addressing on Linux and Windows operating systems. IPC functionality on Windows is restricted to GPUs in TCC mode.
- Parameters:
pHandle- pointer to user allocatedCUipcMemHandleto return the handle indptr- base pointer to previously allocated device memory
-
ncuIpcOpenMemHandle
public static int ncuIpcOpenMemHandle(long pdptr, long handle, int Flags) Unsafe version of:IpcOpenMemHandle -
cuIpcOpenMemHandle
Opens an interprocess memory handle exported from another process and returns a device pointer usable in the local process.Maps memory exported from another process with
IpcGetMemHandleinto the current device address space. For contexts on different devicescuIpcOpenMemHandlecan attempt to enable peer access between the devices as if the user calledCtxEnablePeerAccess. This behavior is controlled by theIPC_MEM_LAZY_ENABLE_PEER_ACCESSflag.DeviceCanAccessPeercan determine if a mapping is possible.Contexts that may open
CUIPCMemHandleare restricted in the following way.CUipcMemHandles from eachCUdevicein a given process may only be opened by oneCUcontextperCUdeviceper other process.If the memory handle has already been opened by the current context, the reference count on the handle is incremented by 1 and the existing device pointer is returned.
Memory returned from
cuIpcOpenMemHandlemust be freed withIpcCloseMemHandle.Calling
MemFreeon an exported memory region before callingcuIpcCloseMemHandlein the importing context will result in undefined behavior.IPC functionality is restricted to devices with support for unified addressing on Linux and Windows operating systems. IPC functionality on Windows is restricted to GPUs in TCC mode.
Note
No guarantees are made about the address returned in
*pdptr. In particular, multiple processes may not receive the same address for the samehandle.- Parameters:
pdptr- returned device pointerhandle-CUipcMemHandleto openFlags- flags for this operation. Must be specified asIPC_MEM_LAZY_ENABLE_PEER_ACCESS.
-
cuIpcCloseMemHandle
public static int cuIpcCloseMemHandle(long dptr) Attempts to close memory mapped withIpcOpenMemHandle.Decrements the reference count of the memory returned by
cuIpcOpenMemHandle()by 1. When the reference count reaches 0, this API unmaps the memory. The original allocation in the exporting process as well as imported mappings in other processes will be unaffected.Any resources used to enable peer access will be freed if this is the last mapping using them.
IPC functionality is restricted to devices with support for unified addressing on Linux and Windows operating systems. IPC functionality on Windows is restricted to GPUs in TCC mode
- Parameters:
dptr- device pointer returned bycuIpcOpenMemHandle()
-
ncuMemHostRegister
public static int ncuMemHostRegister(long p, long bytesize, int Flags) Unsafe version of:MemHostRegister- Parameters:
bytesize- size in bytes of the address range to page-lock
-
cuMemHostRegister
Registers an existing host memory range for use by CUDA.Page-locks the memory range specified by
pandbytesizeand maps it for the device(s) as specified byFlags. This memory range also is added to the same tracking mechanism asMemHostAllocto automatically accelerate calls to functions such asMemcpyHtoD. Since the memory can be accessed directly by the device, it can be read or written with much higher bandwidth than pageable memory that has not been registered. Page-locking excessive amounts of memory may degrade system performance, since it reduces the amount of memory available to the system for paging. As a result, this function is best used sparingly to register staging areas for data exchange between host and device.This function has limited support on Mac OS X. OS 10.7 or higher is required.
All flags are orthogonal to one another: a developer may page-lock memory that is portable or mapped with no restrictions.
The
MEMHOSTREGISTER_DEVICEMAPflag may be specified on CUDA contexts for devices that do not support mapped pinned memory. The failure is deferred toMemHostGetDevicePointerbecause the memory may be mapped into other CUDA contexts via theMEMHOSTREGISTER_PORTABLEflag.For devices that have a non-zero value for the device attribute
DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM, the memory can also be accessed from the device using the host pointerp. The device pointer returned bycuMemHostGetDevicePointer()may or may not match the original host pointerptrand depends on the devices visible to the application. If all devices visible to the application have a non-zero value for the device attribute, the device pointer returned bycuMemHostGetDevicePointer()will match the original pointerptr. If any device visible to the application has a zero value for the device attribute, the device pointer returned bycuMemHostGetDevicePointer()will not match the original host pointerptr, but it will be suitable for use on all devices provided Unified Virtual Addressing is enabled. In such systems, it is valid to access the memory using either pointer on devices that have a non-zero value for the device attribute. Note however that such devices should access the memory using only of the two pointers and not both.The memory page-locked by this function must be unregistered with
MemHostUnregister.- Parameters:
p- host pointer to memory to page-lockFlags- flags for allocation request. One or more of:MEMHOSTREGISTER_PORTABLEMEMHOSTREGISTER_DEVICEMAPMEMHOSTREGISTER_IOMEMORYMEMHOSTREGISTER_READ_ONLY
-
ncuMemHostUnregister
public static int ncuMemHostUnregister(long p) Unsafe version of:MemHostUnregister -
cuMemHostUnregister
Unregisters a memory range that was registered withMemHostRegister.Unmaps the memory range whose base address is specified by
p, and makes it pageable again.The base address must be the same one specified to
MemHostRegister.- Parameters:
p- host pointer to memory to unregister
-
cuMemcpy
public static int cuMemcpy(long dst, long src, long ByteCount) Copies memory.Copies data between two pointers.
dstandsrcare base pointers of the destination and source, respectively.ByteCountspecifies the number of bytes to copy. Note that this function infers the type of the transfer (host to host, host to device, device to device, or device to host) from the pointer values. This function is only allowed in contexts which support unified addressing.- Parameters:
dst- destination unified virtual address space pointersrc- source unified virtual address space pointerByteCount- size of memory copy in bytes
-
cuMemcpyPeer
public static int cuMemcpyPeer(long dstDevice, long dstContext, long srcDevice, long srcContext, long ByteCount) Copies device memory between two contexts.Copies from device memory in one context to device memory in another context.
dstDeviceis the base device pointer of the destination memory anddstContextis the destination context.srcDeviceis the base device pointer of the source memory andsrcContextis the source pointer.ByteCountspecifies the number of bytes to copy.- Parameters:
dstDevice- destination device pointerdstContext- destination contextsrcDevice- source device pointersrcContext- source contextByteCount- size of memory copy in bytes
-
ncuMemcpyHtoD
public static int ncuMemcpyHtoD(long dstDevice, long srcHost, long ByteCount) Unsafe version of:MemcpyHtoD- Parameters:
ByteCount- size of memory copy in bytes
-
cuMemcpyHtoD
Copies memory from Host to Device.Copies from host memory to device memory.
dstDeviceandsrcHostare the base addresses of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstDevice- destination device pointersrcHost- source host pointer
-
cuMemcpyHtoD
Copies memory from Host to Device.Copies from host memory to device memory.
dstDeviceandsrcHostare the base addresses of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstDevice- destination device pointersrcHost- source host pointer
-
cuMemcpyHtoD
Copies memory from Host to Device.Copies from host memory to device memory.
dstDeviceandsrcHostare the base addresses of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstDevice- destination device pointersrcHost- source host pointer
-
cuMemcpyHtoD
Copies memory from Host to Device.Copies from host memory to device memory.
dstDeviceandsrcHostare the base addresses of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstDevice- destination device pointersrcHost- source host pointer
-
cuMemcpyHtoD
Copies memory from Host to Device.Copies from host memory to device memory.
dstDeviceandsrcHostare the base addresses of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstDevice- destination device pointersrcHost- source host pointer
-
cuMemcpyHtoD
Copies memory from Host to Device.Copies from host memory to device memory.
dstDeviceandsrcHostare the base addresses of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstDevice- destination device pointersrcHost- source host pointer
-
cuMemcpyHtoD
Copies memory from Host to Device.Copies from host memory to device memory.
dstDeviceandsrcHostare the base addresses of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstDevice- destination device pointersrcHost- source host pointer
-
ncuMemcpyDtoH
public static int ncuMemcpyDtoH(long dstHost, long srcDevice, long ByteCount) Unsafe version of:MemcpyDtoH- Parameters:
ByteCount- size of memory copy in bytes
-
cuMemcpyDtoH
Copies memory from Device to Host.Copies from device to host memory.
dstHostandsrcDevicespecify the base pointers of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstHost- destination host pointersrcDevice- source device pointer
-
cuMemcpyDtoH
Copies memory from Device to Host.Copies from device to host memory.
dstHostandsrcDevicespecify the base pointers of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstHost- destination host pointersrcDevice- source device pointer
-
cuMemcpyDtoH
Copies memory from Device to Host.Copies from device to host memory.
dstHostandsrcDevicespecify the base pointers of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstHost- destination host pointersrcDevice- source device pointer
-
cuMemcpyDtoH
Copies memory from Device to Host.Copies from device to host memory.
dstHostandsrcDevicespecify the base pointers of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstHost- destination host pointersrcDevice- source device pointer
-
cuMemcpyDtoH
Copies memory from Device to Host.Copies from device to host memory.
dstHostandsrcDevicespecify the base pointers of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstHost- destination host pointersrcDevice- source device pointer
-
cuMemcpyDtoH
Copies memory from Device to Host.Copies from device to host memory.
dstHostandsrcDevicespecify the base pointers of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstHost- destination host pointersrcDevice- source device pointer
-
cuMemcpyDtoH
Copies memory from Device to Host.Copies from device to host memory.
dstHostandsrcDevicespecify the base pointers of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstHost- destination host pointersrcDevice- source device pointer
-
cuMemcpyDtoD
public static int cuMemcpyDtoD(long dstDevice, long srcDevice, long ByteCount) Copies memory from Device to Device.Copies from device memory to device memory.
dstDeviceandsrcDeviceare the base pointers of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstDevice- destination device pointersrcDevice- source device pointerByteCount- size of memory copy in bytes
-
cuMemcpyDtoA
public static int cuMemcpyDtoA(long dstArray, long dstOffset, long srcDevice, long ByteCount) Copies memory from Device to Array.Copies from device memory to a 1D CUDA array.
dstArrayanddstOffsetspecify the CUDA array handle and starting index of the destination data.srcDevicespecifies the base pointer of the source.ByteCountspecifies the number of bytes to copy.- Parameters:
dstArray- destination arraydstOffset- offset in bytes of destination arraysrcDevice- source device pointerByteCount- size of memory copy in bytes
-
cuMemcpyAtoD
public static int cuMemcpyAtoD(long dstDevice, long srcArray, long srcOffset, long ByteCount) Copies memory from Array to Device.Copies from one 1D CUDA array to device memory.
dstDevicespecifies the base pointer of the destination and must be naturally aligned with the CUDA array elements.srcArrayandsrcOffsetspecify the CUDA array handle and the offset in bytes into the array where the copy is to begin.ByteCountspecifies the number of bytes to copy and must be evenly divisible by the array element size.- Parameters:
dstDevice- destination device pointersrcArray- source arraysrcOffset- offset in bytes of source arrayByteCount- size of memory copy in bytes
-
ncuMemcpyHtoA
public static int ncuMemcpyHtoA(long dstArray, long dstOffset, long srcHost, long ByteCount) Unsafe version of:MemcpyHtoA- Parameters:
ByteCount- size of memory copy in bytes
-
cuMemcpyHtoA
Copies memory from Host to Array.Copies from host memory to a 1D CUDA array.
dstArrayanddstOffsetspecify the CUDA array handle and starting offset in bytes of the destination data.pSrcspecifies the base address of the source.ByteCountspecifies the number of bytes to copy.- Parameters:
dstArray- destination arraydstOffset- offset in bytes of destination arraysrcHost- source host pointer
-
cuMemcpyHtoA
Copies memory from Host to Array.Copies from host memory to a 1D CUDA array.
dstArrayanddstOffsetspecify the CUDA array handle and starting offset in bytes of the destination data.pSrcspecifies the base address of the source.ByteCountspecifies the number of bytes to copy.- Parameters:
dstArray- destination arraydstOffset- offset in bytes of destination arraysrcHost- source host pointer
-
cuMemcpyHtoA
Copies memory from Host to Array.Copies from host memory to a 1D CUDA array.
dstArrayanddstOffsetspecify the CUDA array handle and starting offset in bytes of the destination data.pSrcspecifies the base address of the source.ByteCountspecifies the number of bytes to copy.- Parameters:
dstArray- destination arraydstOffset- offset in bytes of destination arraysrcHost- source host pointer
-
cuMemcpyHtoA
Copies memory from Host to Array.Copies from host memory to a 1D CUDA array.
dstArrayanddstOffsetspecify the CUDA array handle and starting offset in bytes of the destination data.pSrcspecifies the base address of the source.ByteCountspecifies the number of bytes to copy.- Parameters:
dstArray- destination arraydstOffset- offset in bytes of destination arraysrcHost- source host pointer
-
cuMemcpyHtoA
Copies memory from Host to Array.Copies from host memory to a 1D CUDA array.
dstArrayanddstOffsetspecify the CUDA array handle and starting offset in bytes of the destination data.pSrcspecifies the base address of the source.ByteCountspecifies the number of bytes to copy.- Parameters:
dstArray- destination arraydstOffset- offset in bytes of destination arraysrcHost- source host pointer
-
cuMemcpyHtoA
Copies memory from Host to Array.Copies from host memory to a 1D CUDA array.
dstArrayanddstOffsetspecify the CUDA array handle and starting offset in bytes of the destination data.pSrcspecifies the base address of the source.ByteCountspecifies the number of bytes to copy.- Parameters:
dstArray- destination arraydstOffset- offset in bytes of destination arraysrcHost- source host pointer
-
cuMemcpyHtoA
Copies memory from Host to Array.Copies from host memory to a 1D CUDA array.
dstArrayanddstOffsetspecify the CUDA array handle and starting offset in bytes of the destination data.pSrcspecifies the base address of the source.ByteCountspecifies the number of bytes to copy.- Parameters:
dstArray- destination arraydstOffset- offset in bytes of destination arraysrcHost- source host pointer
-
ncuMemcpyAtoH
public static int ncuMemcpyAtoH(long dstHost, long srcArray, long srcOffset, long ByteCount) Unsafe version of:MemcpyAtoH- Parameters:
ByteCount- size of memory copy in bytes
-
cuMemcpyAtoH
Copies memory from Array to Host.Copies from one 1D CUDA array to host memory.
dstHostspecifies the base pointer of the destination.srcArrayandsrcOffsetspecify the CUDA array handle and starting offset in bytes of the source data.ByteCountspecifies the number of bytes to copy.- Parameters:
dstHost- destination device pointersrcArray- source arraysrcOffset- offset in bytes of source array
-
cuMemcpyAtoH
Copies memory from Array to Host.Copies from one 1D CUDA array to host memory.
dstHostspecifies the base pointer of the destination.srcArrayandsrcOffsetspecify the CUDA array handle and starting offset in bytes of the source data.ByteCountspecifies the number of bytes to copy.- Parameters:
dstHost- destination device pointersrcArray- source arraysrcOffset- offset in bytes of source array
-
cuMemcpyAtoH
Copies memory from Array to Host.Copies from one 1D CUDA array to host memory.
dstHostspecifies the base pointer of the destination.srcArrayandsrcOffsetspecify the CUDA array handle and starting offset in bytes of the source data.ByteCountspecifies the number of bytes to copy.- Parameters:
dstHost- destination device pointersrcArray- source arraysrcOffset- offset in bytes of source array
-
cuMemcpyAtoH
Copies memory from Array to Host.Copies from one 1D CUDA array to host memory.
dstHostspecifies the base pointer of the destination.srcArrayandsrcOffsetspecify the CUDA array handle and starting offset in bytes of the source data.ByteCountspecifies the number of bytes to copy.- Parameters:
dstHost- destination device pointersrcArray- source arraysrcOffset- offset in bytes of source array
-
cuMemcpyAtoH
Copies memory from Array to Host.Copies from one 1D CUDA array to host memory.
dstHostspecifies the base pointer of the destination.srcArrayandsrcOffsetspecify the CUDA array handle and starting offset in bytes of the source data.ByteCountspecifies the number of bytes to copy.- Parameters:
dstHost- destination device pointersrcArray- source arraysrcOffset- offset in bytes of source array
-
cuMemcpyAtoH
Copies memory from Array to Host.Copies from one 1D CUDA array to host memory.
dstHostspecifies the base pointer of the destination.srcArrayandsrcOffsetspecify the CUDA array handle and starting offset in bytes of the source data.ByteCountspecifies the number of bytes to copy.- Parameters:
dstHost- destination device pointersrcArray- source arraysrcOffset- offset in bytes of source array
-
cuMemcpyAtoH
Copies memory from Array to Host.Copies from one 1D CUDA array to host memory.
dstHostspecifies the base pointer of the destination.srcArrayandsrcOffsetspecify the CUDA array handle and starting offset in bytes of the source data.ByteCountspecifies the number of bytes to copy.- Parameters:
dstHost- destination device pointersrcArray- source arraysrcOffset- offset in bytes of source array
-
cuMemcpyAtoA
public static int cuMemcpyAtoA(long dstArray, long dstOffset, long srcArray, long srcOffset, long ByteCount) Copies memory from Array to Array.Copies from one 1D CUDA array to another.
dstArrayandsrcArrayspecify the handles of the destination and source CUDA arrays for the copy, respectively.dstOffsetandsrcOffsetspecify the destination and source offsets in bytes into the CUDA arrays.ByteCountis the number of bytes to be copied. The size of the elements in the CUDA arrays need not be the same format, but the elements must be the same size; and count must be evenly divisible by that size.- Parameters:
dstArray- destination arraydstOffset- offset in bytes of destination arraysrcArray- source arraysrcOffset- offset in bytes of source arrayByteCount- size of memory copy in bytes
-
ncuMemcpy2D
public static int ncuMemcpy2D(long pCopy) Unsafe version of:Memcpy2D -
cuMemcpy2D
Copies memory for 2D arrays.Perform a 2D memory copy according to the parameters specified in
pCopy.If
srcMemoryTypeisMEMORYTYPE_UNIFIED,srcDeviceandsrcPitchspecify the (unified virtual address space) base address of the source data and the bytes per row to apply.srcArrayis ignored. This value may be used only if unified addressing is supported in the calling context.If
srcMemoryTypeisMEMORYTYPE_HOST,srcHostandsrcPitchspecify the (host) base address of the source data and the bytes per row to apply.srcArrayis ignored.If
srcMemoryTypeisMEMORYTYPE_DEVICE,srcDeviceandsrcPitchspecify the (device) base address of the source data and the bytes per row to apply.srcArrayis ignored.If
srcMemoryTypeisMEMORYTYPE_ARRAY,srcArrayspecifies the handle of the source data.srcHost,srcDeviceandsrcPitchare ignored.If
dstMemoryTypeisMEMORYTYPE_HOST,dstHostanddstPitchspecify the (host) base address of the destination data and the bytes per row to apply.dstArrayis ignored.If
dstMemoryTypeisMEMORYTYPE_UNIFIED,dstDeviceanddstPitchspecify the (unified virtual address space) base address of the source data and the bytes per row to apply.dstArrayis ignored. This value may be used only if unified addressing is supported in the calling context.If
dstMemoryTypeisMEMORYTYPE_DEVICE,dstDeviceanddstPitchspecify the (device) base address of the destination data and the bytes per row to apply.dstArrayis ignored.If
dstMemoryTypeisMEMORYTYPE_ARRAY,dstArrayspecifies the handle of the destination data.dstHost,dstDeviceanddstPitchare ignored.srcXInBytesandsrcYspecify the base address of the source data for the copy.For host pointers, the starting address is
voidStart = (void*)((char*)srcHost+srcY*srcPitch + srcXInBytes);For device pointers, the starting address is
CUdeviceptr Start = srcDevice+srcY*srcPitch+srcXInBytes;For CUDA arrays,
srcXInBytesmust be evenly divisible by the array element size.dstXInBytesanddstYspecify the base address of the destination data for the copy.For host pointers, the base address is
voiddstStart = (void*)((char*)dstHost+dstY*dstPitch + dstXInBytes);For device pointers, the starting address is
CUdeviceptr dstStart = dstDevice+dstY*dstPitch+dstXInBytes;For CUDA arrays,
dstXInBytesmust be evenly divisible by the array element size.WidthInBytesandHeightspecify the width (in bytes) and height of the 2D copy being performed.If specified,
srcPitchmust be greater than or equal toWidthInBytes+srcXInBytes, anddstPitchmust be greater than or equal toWidthInBytes+dstXInBytes.cuMemcpy2D()returns an error if any pitch is greater than the maximum allowed (DEVICE_ATTRIBUTE_MAX_PITCH).cuMemAllocPitch() passes back pitches that always work withcuMemcpy2D(). On intra-device memory copies (device to device, CUDA array to device, CUDA array to CUDA array),cuMemcpy2D()may fail for pitches not computed byMemAllocPitch.Memcpy2DUnaligneddoes not have this restriction, but may run significantly slower in the cases wherecuMemcpy2D()would have returned an error code.- Parameters:
pCopy- parameters for the memory copy
-
ncuMemcpy2DUnaligned
public static int ncuMemcpy2DUnaligned(long pCopy) Unsafe version of:Memcpy2DUnaligned -
cuMemcpy2DUnaligned
Copies memory for 2D arrays.Perform a 2D memory copy according to the parameters specified in
pCopy.If
srcMemoryTypeisMEMORYTYPE_UNIFIED,srcDeviceandsrcPitchspecify the (unified virtual address space) base address of the source data and the bytes per row to apply.srcArrayis ignored. This value may be used only if unified addressing is supported in the calling context.If
srcMemoryTypeisMEMORYTYPE_HOST,srcHostandsrcPitchspecify the (host) base address of the source data and the bytes per row to apply.srcArrayis ignored.If
srcMemoryTypeisMEMORYTYPE_DEVICE,srcDeviceandsrcPitchspecify the (device) base address of the source data and the bytes per row to apply.srcArrayis ignored.If
srcMemoryTypeisMEMORYTYPE_ARRAY,srcArrayspecifies the handle of the source data.srcHost,srcDeviceandsrcPitchare ignored.If
dstMemoryTypeisMEMORYTYPE_UNIFIED,dstDeviceanddstPitchspecify the (unified virtual address space) base address of the source data and the bytes per row to apply.dstArrayis ignored. This value may be used only if unified addressing is supported in the calling context.If
dstMemoryTypeisMEMORYTYPE_HOST,dstHostanddstPitchspecify the (host) base address of the destination data and the bytes per row to apply.dstArrayis ignored.If
dstMemoryTypeisMEMORYTYPE_DEVICE,dstDeviceanddstPitchspecify the (device) base address of the destination data and the bytes per row to apply.dstArrayis ignored.If
dstMemoryTypeisMEMORYTYPE_ARRAY,dstArrayspecifies the handle of the destination data.dstHost,dstDeviceanddstPitchare ignored.srcXInBytesandsrcYspecify the base address of the source data for the copy.For host pointers, the starting address is
void* Start = (void*)((char*)srcHost+srcY*srcPitch + srcXInBytes);For device pointers, the starting address is
CUdeviceptr Start = srcDevice+srcY*srcPitch+srcXInBytes;For CUDA arrays,
srcXInBytesmust be evenly divisible by the array element size.dstXInBytesanddstYspecify the base address of the destination data for the copy.For host pointers, the base address is
void* dstStart = (void*)((char*)dstHost+dstY*dstPitch + dstXInBytes);For device pointers, the starting address is
CUdeviceptr dstStart = dstDevice+dstY*dstPitch+dstXInBytes;For CUDA arrays,
dstXInBytesmust be evenly divisible by the array element size.WidthInBytesandHeightspecify the width (in bytes) and height of the 2D copy being performed.If specified,
srcPitchmust be greater than or equal toWidthInBytes+srcXInBytes, anddstPitchmust be greater than or equal toWidthInBytes+dstXInBytes.Memcpy2Dreturns an error if any pitch is greater than the maximum allowed (DEVICE_ATTRIBUTE_MAX_PITCH).MemAllocPitchpasses back pitches that always work withcuMemcpy2D(). On intra-device memory copies (device to device, CUDA array to device, CUDA array to CUDA array),cuMemcpy2D()may fail for pitches not computed bycuMemAllocPitch().cuMemcpy2DUnaligned()does not have this restriction, but may run significantly slower in the cases wherecuMemcpy2D()would have returned an error code.- Parameters:
pCopy- parameters for the memory copy
-
ncuMemcpy3D
public static int ncuMemcpy3D(long pCopy) Unsafe version of:Memcpy3D -
cuMemcpy3D
Copies memory for 3D arrays.Perform a 3D memory copy according to the parameters specified in
pCopy.If
srcMemoryTypeisMEMORYTYPE_UNIFIED,srcDeviceandsrcPitchspecify the (unified virtual address space) base address of the source data and the bytes per row to apply.srcArrayis ignored. This value may be used only if unified addressing is supported in the calling context.If
srcMemoryTypeisMEMORYTYPE_HOST,srcHost,srcPitchandsrcHeightspecify the (host) base address of the source data, the bytes per row, and the height of each 2D slice of the 3D array.srcArrayis ignored.If
srcMemoryTypeisMEMORYTYPE_DEVICE,srcDevice,srcPitchandsrcHeightspecify the (device) base address of the source data, the bytes per row, and the height of each 2D slice of the 3D array.srcArrayis ignored.If
srcMemoryTypeisMEMORYTYPE_ARRAY,srcArrayspecifies the handle of the source data.srcHost,srcDevice,srcPitchandsrcHeightare ignored.If
dstMemoryTypeisMEMORYTYPE_UNIFIED,dstDeviceanddstPitchspecify the (unified virtual address space) base address of the source data and the bytes per row to apply.dstArrayis ignored. This value may be used only if unified addressing is supported in the calling context.If
dstMemoryTypeisMEMORYTYPE_HOST,dstHostanddstPitchspecify the (host) base address of the destination data, the bytes per row, and the height of each 2D slice of the 3D array.dstArrayis ignored.If
dstMemoryTypeisMEMORYTYPE_DEVICE,dstDeviceanddstPitchspecify the (device) base address of the destination data, the bytes per row, and the height of each 2D slice of the 3D array.dstArrayis ignored.If
dstMemoryTypeisMEMORYTYPE_ARRAY,dstArrayspecifies the handle of the destination data.dstHost,dstDevice,dstPitchanddstHeightare ignored.srcXInBytes,srcYandsrcZspecify the base address of the source data for the copy.For host pointers, the starting address is
void* Start = (void*)((char*)srcHost+(srcZ*srcHeight+srcY)*srcPitch + srcXInBytes);For device pointers, the starting address is
CUdeviceptr Start = srcDevice+(srcZ*srcHeight+srcY)*srcPitch+srcXInBytes;For CUDA arrays,
srcXInBytesmust be evenly divisible by the array element size.dstXInBytes,dstYanddstZspecify the base address of the destination data for the copy.For host pointers, the base address is
void* dstStart = (void*)((char*)dstHost+(dstZ*dstHeight+dstY)*dstPitch + dstXInBytes);For device pointers, the starting address is
CUdeviceptr dstStart = dstDevice+(dstZ*dstHeight+dstY)*dstPitch+dstXInBytes;For CUDA arrays,
dstXInBytesmust be evenly divisible by the array element size.WidthInBytes,HeightandDepthspecify the width (in bytes), height and depth of the 3D copy being performed.If specified,
srcPitchmust be greater than or equal toWidthInBytes+srcXInBytes, anddstPitchmust be greater than or equal toWidthInBytes+dstXInBytes.If specified,
srcHeightmust be greater than or equal toHeight+srcY, anddstHeightmust be greater than or equal toHeight+dstY.Memcpy3Dreturns an error if any pitch is greater than the maximum allowed (DEVICE_ATTRIBUTE_MAX_PITCH).The
srcLODanddstLODmembers of theCUDA_MEMCPY3Dstructure must be set to 0.Note
_sync
- Parameters:
pCopy- parameters for the memory copy
-
ncuMemcpy3DPeer
public static int ncuMemcpy3DPeer(long pCopy) Unsafe version of:Memcpy3DPeer -
cuMemcpy3DPeer
Copies memory between contexts.Perform a 3D memory copy according to the parameters specified in
pCopy.- Parameters:
pCopy- parameters for the memory copy
-
cuMemcpyAsync
public static int cuMemcpyAsync(long dst, long src, long ByteCount, long hStream) Copies memory asynchronously.Copies data between two pointers.
dstandsrcare base pointers of the destination and source, respectively.ByteCountspecifies the number of bytes to copy. Note that this function infers the type of the transfer (host to host, host to device, device to device, or device to host) from the pointer values. This function is only allowed in contexts which support unified addressing.- Parameters:
dst- destination unified virtual address space pointersrc- source unified virtual address space pointerByteCount- size of memory copy in byteshStream- stream identifier
-
cuMemcpyPeerAsync
public static int cuMemcpyPeerAsync(long dstDevice, long dstContext, long srcDevice, long srcContext, long ByteCount, long hStream) Copies device memory between two contexts asynchronously.Copies from device memory in one context to device memory in another context.
dstDeviceis the base device pointer of the destination memory anddstContextis the destination context.srcDeviceis the base device pointer of the source memory andsrcContextis the source pointer.ByteCountspecifies the number of bytes to copy.- Parameters:
dstDevice- destination device pointerdstContext- destination contextsrcDevice- source device pointersrcContext- source contextByteCount- size of memory copy in byteshStream- stream identifier
-
ncuMemcpyHtoDAsync
public static int ncuMemcpyHtoDAsync(long dstDevice, long srcHost, long ByteCount, long hStream) Unsafe version of:MemcpyHtoDAsync- Parameters:
ByteCount- size of memory copy in bytes
-
cuMemcpyHtoDAsync
Copies memory from Host to Device.Copies from host memory to device memory.
dstDeviceandsrcHostare the base addresses of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstDevice- destination device pointersrcHost- source host pointerhStream- stream identifier
-
cuMemcpyHtoDAsync
Copies memory from Host to Device.Copies from host memory to device memory.
dstDeviceandsrcHostare the base addresses of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstDevice- destination device pointersrcHost- source host pointerhStream- stream identifier
-
cuMemcpyHtoDAsync
Copies memory from Host to Device.Copies from host memory to device memory.
dstDeviceandsrcHostare the base addresses of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstDevice- destination device pointersrcHost- source host pointerhStream- stream identifier
-
cuMemcpyHtoDAsync
Copies memory from Host to Device.Copies from host memory to device memory.
dstDeviceandsrcHostare the base addresses of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstDevice- destination device pointersrcHost- source host pointerhStream- stream identifier
-
cuMemcpyHtoDAsync
Copies memory from Host to Device.Copies from host memory to device memory.
dstDeviceandsrcHostare the base addresses of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstDevice- destination device pointersrcHost- source host pointerhStream- stream identifier
-
cuMemcpyHtoDAsync
Copies memory from Host to Device.Copies from host memory to device memory.
dstDeviceandsrcHostare the base addresses of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstDevice- destination device pointersrcHost- source host pointerhStream- stream identifier
-
cuMemcpyHtoDAsync
Copies memory from Host to Device.Copies from host memory to device memory.
dstDeviceandsrcHostare the base addresses of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstDevice- destination device pointersrcHost- source host pointerhStream- stream identifier
-
ncuMemcpyDtoHAsync
public static int ncuMemcpyDtoHAsync(long dstHost, long srcDevice, long ByteCount, long hStream) Unsafe version of:MemcpyDtoHAsync- Parameters:
ByteCount- size of memory copy in bytes
-
cuMemcpyDtoHAsync
Copies memory from Device to Host.Copies from device to host memory.
dstHostandsrcDevicespecify the base pointers of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstHost- destination host pointersrcDevice- source device pointerhStream- stream identifier
-
cuMemcpyDtoHAsync
Copies memory from Device to Host.Copies from device to host memory.
dstHostandsrcDevicespecify the base pointers of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstHost- destination host pointersrcDevice- source device pointerhStream- stream identifier
-
cuMemcpyDtoHAsync
Copies memory from Device to Host.Copies from device to host memory.
dstHostandsrcDevicespecify the base pointers of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstHost- destination host pointersrcDevice- source device pointerhStream- stream identifier
-
cuMemcpyDtoHAsync
Copies memory from Device to Host.Copies from device to host memory.
dstHostandsrcDevicespecify the base pointers of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstHost- destination host pointersrcDevice- source device pointerhStream- stream identifier
-
cuMemcpyDtoHAsync
Copies memory from Device to Host.Copies from device to host memory.
dstHostandsrcDevicespecify the base pointers of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstHost- destination host pointersrcDevice- source device pointerhStream- stream identifier
-
cuMemcpyDtoHAsync
Copies memory from Device to Host.Copies from device to host memory.
dstHostandsrcDevicespecify the base pointers of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstHost- destination host pointersrcDevice- source device pointerhStream- stream identifier
-
cuMemcpyDtoHAsync
Copies memory from Device to Host.Copies from device to host memory.
dstHostandsrcDevicespecify the base pointers of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstHost- destination host pointersrcDevice- source device pointerhStream- stream identifier
-
cuMemcpyDtoDAsync
public static int cuMemcpyDtoDAsync(long dstDevice, long srcDevice, long ByteCount, long hStream) Copies memory from Device to Device.Copies from device memory to device memory.
dstDeviceandsrcDeviceare the base pointers of the destination and source, respectively.ByteCountspecifies the number of bytes to copy.- Parameters:
dstDevice- destination device pointersrcDevice- source device pointerByteCount- size of memory copy in byteshStream- stream identifier
-
ncuMemcpyHtoAAsync
public static int ncuMemcpyHtoAAsync(long dstArray, long dstOffset, long srcHost, long ByteCount, long hStream) Unsafe version of:MemcpyHtoAAsync- Parameters:
ByteCount- size of memory copy in bytes
-
cuMemcpyHtoAAsync
public static int cuMemcpyHtoAAsync(long dstArray, long dstOffset, ByteBuffer srcHost, long hStream) Copies memory from Host to Array.Copies from host memory to a 1D CUDA array.
dstArrayanddstOffsetspecify the CUDA array handle and starting offset in bytes of the destination data.srcHostspecifies the base address of the source.ByteCountspecifies the number of bytes to copy.- Parameters:
dstArray- destination arraydstOffset- offset in bytes of destination arraysrcHost- source host pointerhStream- stream identifier
-
cuMemcpyHtoAAsync
public static int cuMemcpyHtoAAsync(long dstArray, long dstOffset, ShortBuffer srcHost, long hStream) Copies memory from Host to Array.Copies from host memory to a 1D CUDA array.
dstArrayanddstOffsetspecify the CUDA array handle and starting offset in bytes of the destination data.srcHostspecifies the base address of the source.ByteCountspecifies the number of bytes to copy.- Parameters:
dstArray- destination arraydstOffset- offset in bytes of destination arraysrcHost- source host pointerhStream- stream identifier
-
cuMemcpyHtoAAsync
Copies memory from Host to Array.Copies from host memory to a 1D CUDA array.
dstArrayanddstOffsetspecify the CUDA array handle and starting offset in bytes of the destination data.srcHostspecifies the base address of the source.ByteCountspecifies the number of bytes to copy.- Parameters:
dstArray- destination arraydstOffset- offset in bytes of destination arraysrcHost- source host pointerhStream- stream identifier
-
cuMemcpyHtoAAsync
public static int cuMemcpyHtoAAsync(long dstArray, long dstOffset, LongBuffer srcHost, long hStream) Copies memory from Host to Array.Copies from host memory to a 1D CUDA array.
dstArrayanddstOffsetspecify the CUDA array handle and starting offset in bytes of the destination data.srcHostspecifies the base address of the source.ByteCountspecifies the number of bytes to copy.- Parameters:
dstArray- destination arraydstOffset- offset in bytes of destination arraysrcHost- source host pointerhStream- stream identifier
-
cuMemcpyHtoAAsync
public static int cuMemcpyHtoAAsync(long dstArray, long dstOffset, FloatBuffer srcHost, long hStream) Copies memory from Host to Array.Copies from host memory to a 1D CUDA array.
dstArrayanddstOffsetspecify the CUDA array handle and starting offset in bytes of the destination data.srcHostspecifies the base address of the source.ByteCountspecifies the number of bytes to copy.- Parameters:
dstArray- destination arraydstOffset- offset in bytes of destination arraysrcHost- source host pointerhStream- stream identifier
-
cuMemcpyHtoAAsync
public static int cuMemcpyHtoAAsync(long dstArray, long dstOffset, DoubleBuffer srcHost, long hStream) Copies memory from Host to Array.Copies from host memory to a 1D CUDA array.
dstArrayanddstOffsetspecify the CUDA array handle and starting offset in bytes of the destination data.srcHostspecifies the base address of the source.ByteCountspecifies the number of bytes to copy.- Parameters:
dstArray- destination arraydstOffset- offset in bytes of destination arraysrcHost- source host pointerhStream- stream identifier
-
cuMemcpyHtoAAsync
public static int cuMemcpyHtoAAsync(long dstArray, long dstOffset, PointerBuffer srcHost, long hStream) Copies memory from Host to Array.Copies from host memory to a 1D CUDA array.
dstArrayanddstOffsetspecify the CUDA array handle and starting offset in bytes of the destination data.srcHostspecifies the base address of the source.ByteCountspecifies the number of bytes to copy.- Parameters:
dstArray- destination arraydstOffset- offset in bytes of destination arraysrcHost- source host pointerhStream- stream identifier
-
ncuMemcpyAtoHAsync
public static int ncuMemcpyAtoHAsync(long dstHost, long srcArray, long srcOffset, long ByteCount, long hStream) Unsafe version of:MemcpyAtoHAsync- Parameters:
ByteCount- size of memory copy in bytes
-
cuMemcpyAtoHAsync
public static int cuMemcpyAtoHAsync(ByteBuffer dstHost, long srcArray, long srcOffset, long hStream) Copies memory from Array to Host.Copies from one 1D CUDA array to host memory.
dstHostspecifies the base pointer of the destination.srcArrayandsrcOffsetspecify the CUDA array handle and starting offset in bytes of the source data.ByteCountspecifies the number of bytes to copy.- Parameters:
dstHost- destination pointersrcArray- source arraysrcOffset- offset in bytes of source arrayhStream- stream identifier
-
cuMemcpyAtoHAsync
public static int cuMemcpyAtoHAsync(ShortBuffer dstHost, long srcArray, long srcOffset, long hStream) Copies memory from Array to Host.Copies from one 1D CUDA array to host memory.
dstHostspecifies the base pointer of the destination.srcArrayandsrcOffsetspecify the CUDA array handle and starting offset in bytes of the source data.ByteCountspecifies the number of bytes to copy.- Parameters:
dstHost- destination pointersrcArray- source arraysrcOffset- offset in bytes of source arrayhStream- stream identifier
-
cuMemcpyAtoHAsync
Copies memory from Array to Host.Copies from one 1D CUDA array to host memory.
dstHostspecifies the base pointer of the destination.srcArrayandsrcOffsetspecify the CUDA array handle and starting offset in bytes of the source data.ByteCountspecifies the number of bytes to copy.- Parameters:
dstHost- destination pointersrcArray- source arraysrcOffset- offset in bytes of source arrayhStream- stream identifier
-
cuMemcpyAtoHAsync
public static int cuMemcpyAtoHAsync(LongBuffer dstHost, long srcArray, long srcOffset, long hStream) Copies memory from Array to Host.Copies from one 1D CUDA array to host memory.
dstHostspecifies the base pointer of the destination.srcArrayandsrcOffsetspecify the CUDA array handle and starting offset in bytes of the source data.ByteCountspecifies the number of bytes to copy.- Parameters:
dstHost- destination pointersrcArray- source arraysrcOffset- offset in bytes of source arrayhStream- stream identifier
-
cuMemcpyAtoHAsync
public static int cuMemcpyAtoHAsync(FloatBuffer dstHost, long srcArray, long srcOffset, long hStream) Copies memory from Array to Host.Copies from one 1D CUDA array to host memory.
dstHostspecifies the base pointer of the destination.srcArrayandsrcOffsetspecify the CUDA array handle and starting offset in bytes of the source data.ByteCountspecifies the number of bytes to copy.- Parameters:
dstHost- destination pointersrcArray- source arraysrcOffset- offset in bytes of source arrayhStream- stream identifier
-
cuMemcpyAtoHAsync
public static int cuMemcpyAtoHAsync(DoubleBuffer dstHost, long srcArray, long srcOffset, long hStream) Copies memory from Array to Host.Copies from one 1D CUDA array to host memory.
dstHostspecifies the base pointer of the destination.srcArrayandsrcOffsetspecify the CUDA array handle and starting offset in bytes of the source data.ByteCountspecifies the number of bytes to copy.- Parameters:
dstHost- destination pointersrcArray- source arraysrcOffset- offset in bytes of source arrayhStream- stream identifier
-
cuMemcpyAtoHAsync
public static int cuMemcpyAtoHAsync(PointerBuffer dstHost, long srcArray, long srcOffset, long hStream) Copies memory from Array to Host.Copies from one 1D CUDA array to host memory.
dstHostspecifies the base pointer of the destination.srcArrayandsrcOffsetspecify the CUDA array handle and starting offset in bytes of the source data.ByteCountspecifies the number of bytes to copy.- Parameters:
dstHost- destination pointersrcArray- source arraysrcOffset- offset in bytes of source arrayhStream- stream identifier
-
ncuMemcpy2DAsync
public static int ncuMemcpy2DAsync(long pCopy, long hStream) Unsafe version of:Memcpy2DAsync -
cuMemcpy2DAsync
Copies memory for 2D arrays.Perform a 2D memory copy according to the parameters specified in
pCopy.If
srcMemoryTypeisMEMORYTYPE_HOST,srcHostandsrcPitchspecify the (host) base address of the source data and the bytes per row to apply.srcArrayis ignored.If
srcMemoryTypeisMEMORYTYPE_UNIFIED,srcDeviceandsrcPitchspecify the (unified virtual address space) base address of the source data and the bytes per row to apply.srcArrayis ignored. This value may be used only if unified addressing is supported in the calling context.If
srcMemoryTypeisMEMORYTYPE_DEVICE,srcDeviceandsrcPitchspecify the (device) base address of the source data and the bytes per row to apply.srcArrayis ignored.If
srcMemoryTypeisMEMORYTYPE_ARRAY,srcArrayspecifies the handle of the source data.srcHost,srcDeviceandsrcPitchare ignored.If
dstMemoryTypeisMEMORYTYPE_UNIFIED,dstDeviceanddstPitchspecify the (unified virtual address space) base address of the source data and the bytes per row to apply.dstArrayis ignored. This value may be used only if unified addressing is supported in the calling context.If
dstMemoryTypeisMEMORYTYPE_HOST,dstHostanddstPitchspecify the (host) base address of the destination data and the bytes per row to apply.dstArrayis ignored.If
dstMemoryTypeisMEMORYTYPE_DEVICE,dstDeviceanddstPitchspecify the (device) base address of the destination data and the bytes per row to apply.dstArrayis ignored.If
dstMemoryTypeisMEMORYTYPE_ARRAY,dstArrayspecifies the handle of the destination data.dstHost,dstDeviceanddstPitchare ignored.srcXInBytesandsrcYspecify the base address of the source data for the copy.For host pointers, the starting address is
void* Start = (void*)((char*)srcHost+srcY*srcPitch + srcXInBytes);For device pointers, the starting address is
CUdeviceptr Start = srcDevice+srcY*srcPitch+srcXInBytes;For CUDA arrays,
srcXInBytesmust be evenly divisible by the array element size.dstXInBytesanddstYspecify the base address of the destination data for the copy.For host pointers, the base address is
void* dstStart = (void*)((char*)dstHost+dstY*dstPitch + dstXInBytes);For device pointers, the starting address is
CUdeviceptr dstStart = dstDevice+dstY*dstPitch+dstXInBytes;For CUDA arrays,
dstXInBytesmust be evenly divisible by the array element size.WidthInBytesandHeightspecify the width (in bytes) and height of the 2D copy being performed.If specified,
srcPitchmust be greater than or equal toWidthInBytes+srcXInBytes, anddstPitchmust be greater than or equal toWidthInBytes+dstXInBytes.If specified,
srcPitchmust be greater than or equal toWidthInBytes+srcXInBytes, anddstPitchmust be greater than or equal toWidthInBytes+dstXInBytes.If specified,
srcHeightmust be greater than or equal toHeight+srcY, anddstHeightmust be greater than or equal toHeight+dstY.cuMemcpy2DAsync()returns an error if any pitch is greater than the maximum allowed (DEVICE_ATTRIBUTE_MAX_PITCH).MemAllocPitchpasses back pitches that always work withMemcpy2D. On intra-device memory copies (device to device, CUDA array to device, CUDA array to CUDA array),cuMemcpy2DAsync()may fail for pitches not computed bycuMemAllocPitch().- Parameters:
pCopy- parameters for the memory copyhStream- stream identifier
-
ncuMemcpy3DAsync
public static int ncuMemcpy3DAsync(long pCopy, long hStream) Unsafe version of:Memcpy3DAsync -
cuMemcpy3DAsync
Copies memory for 3D arrays.Perform a 3D memory copy according to the parameters specified in
pCopy.If
srcMemoryTypeisMEMORYTYPE_UNIFIED,srcDeviceandsrcPitchspecify the (unified virtual address space) base address of the source data and the bytes per row to apply.srcArrayis ignored. This value may be used only if unified addressing is supported in the calling context.If
srcMemoryTypeisMEMORYTYPE_HOST,srcHost,srcPitchandsrcHeightspecify the (host) base address of the source data, the bytes per row, and the height of each 2D slice of the 3D array.srcArrayis ignored.If
srcMemoryTypeisMEMORYTYPE_DEVICE,srcDevice,srcPitchandsrcHeightspecify the (device) base address of the source data, the bytes per row, and the height of each 2D slice of the 3D array.srcArrayis ignored.If
srcMemoryTypeisMEMORYTYPE_ARRAY,srcArrayspecifies the handle of the source data.srcHost,srcDevice,srcPitchandsrcHeightare ignored.If
dstMemoryTypeisMEMORYTYPE_UNIFIED,dstDeviceanddstPitchspecify the (unified virtual address space) base address of the source data and the bytes per row to apply.dstArrayis ignored. This value may be used only if unified addressing is supported in the calling context.If
dstMemoryTypeisMEMORYTYPE_HOST,dstHostanddstPitchspecify the (host) base address of the destination data, the bytes per row, and the height of each 2D slice of the 3D array.dstArrayis ignored.If
dstMemoryTypeisMEMORYTYPE_DEVICE,dstDeviceanddstPitchspecify the (device) base address of the destination data, the bytes per row, and the height of each 2D slice of the 3D array.dstArrayis ignored.If
dstMemoryTypeisMEMORYTYPE_ARRAY,dstArrayspecifies the handle of the destination data.dstHost,dstDevice,dstPitchanddstHeightare ignored.-
srcXInBytes,srcYandsrcZspecify the base address of the source data for the copy.For host pointers, the starting address is
void* Start = (void*)((char*)srcHost+(srcZ*srcHeight+srcY)*srcPitch + srcXInBytes);For device pointers, the starting address is
CUdeviceptr Start = srcDevice+(srcZ*srcHeight+srcY)*srcPitch+srcXInBytes;For CUDA arrays,
srcXInBytesmust be evenly divisible by the array element size.dstXInBytes,dstYanddstZspecify the base address of the destination data for the copy.For host pointers, the base address is
void* dstStart = (void*)((char*)dstHost+(dstZ*dstHeight+dstY)*dstPitch + dstXInBytes);For device pointers, the starting address is
CUdeviceptr dstStart = dstDevice+(dstZ*dstHeight+dstY)*dstPitch+dstXInBytes;For CUDA arrays,
dstXInBytesmust be evenly divisible by the array element size.WidthInBytes,HeightandDepthspecify the width (in bytes), height and depth of the 3D copy being performed.If specified,
srcPitchmust be greater than or equal toWidthInBytes+srcXInBytes, anddstPitchmust be greater than or equal toWidthInBytes+dstXInBytes.If specified,
srcHeightmust be greater than or equal toHeight+srcY, anddstHeightmust be greater than or equal toHeight+dstY.Memcpy3DAsyncreturns an error if any pitch is greater than the maximum allowed (DEVICE_ATTRIBUTE_MAX_PITCH).The
srcLODanddstLODmembers of theCUDA_MEMCPY3Dstructure must be set to 0.- Parameters:
pCopy- parameters for the memory copyhStream- stream identifier
-
ncuMemcpy3DPeerAsync
public static int ncuMemcpy3DPeerAsync(long pCopy, long hStream) Unsafe version of:Memcpy3DPeerAsync -
cuMemcpy3DPeerAsync
Copies memory between contexts asynchronously.Perform a 3D memory copy according to the parameters specified in
pCopy.- Parameters:
pCopy- parameters for the memory copyhStream- stream identifier
-
cuMemsetD8
public static int cuMemsetD8(long dstDevice, byte uc, long N) Initializes device memory.Sets the memory range of
N8-bit values to the specified valueuc.- Parameters:
dstDevice- destination device pointeruc- value to setN- number of elements
-
cuMemsetD16
public static int cuMemsetD16(long dstDevice, short us, long N) Initializes device memory.Sets the memory range of
N16-bit values to the specified valueus. ThedstDevicepointer must be two byte aligned.- Parameters:
dstDevice- destination device pointerus- value to setN- number of elements
-
cuMemsetD32
public static int cuMemsetD32(long dstDevice, int ui, long N) Initializes device memorySets the memory range of
N32-bit values to the specified valueui. ThedstDevicepointer must be four byte aligned.- Parameters:
dstDevice- destination device pointerui- value to setN- number of elements
-
cuMemsetD2D8
public static int cuMemsetD2D8(long dstDevice, long dstPitch, byte uc, long Width, long Height) Initializes device memory.Sets the 2D memory range of
Width8-bit values to the specified valueuc.Heightspecifies the number of rows to set, anddstPitchspecifies the number of bytes between each row. This function performs fastest when the pitch is one that has been passed back byMemAllocPitch.- Parameters:
dstDevice- destination device pointerdstPitch- pitch of destination device pointer(Unused ifHeightis 1)uc- value to setWidth- width of rowHeight- number of rows
-
cuMemsetD2D16
public static int cuMemsetD2D16(long dstDevice, long dstPitch, short us, long Width, long Height) Initializes device memory.Sets the 2D memory range of
Width16-bit values to the specified valueus.Heightspecifies the number of rows to set, anddstPitchspecifies the number of bytes between each row. ThedstDevicepointer anddstPitchoffset must be two byte aligned. This function performs fastest when the pitch is one that has been passed back byMemAllocPitch.- Parameters:
dstDevice- destination device pointerdstPitch- pitch of destination device pointer(Unused ifHeightis 1)us- value to setWidth- width of rowHeight- number of rows
-
cuMemsetD2D32
public static int cuMemsetD2D32(long dstDevice, long dstPitch, int ui, long Width, long Height) Initializes device memory.Sets the 2D memory range of
Width32-bit values to the specified valueui.Heightspecifies the number of rows to set, anddstPitchspecifies the number of bytes between each row. ThedstDevicepointer anddstPitchoffset must be four byte aligned. This function performs fastest when the pitch is one that has been passed back byMemAllocPitch.- Parameters:
dstDevice- destination device pointerdstPitch- pitch of destination device pointer(Unused ifHeightis 1)ui- value to setWidth- width of rowHeight- number of rows
-
cuMemsetD8Async
public static int cuMemsetD8Async(long dstDevice, byte uc, long N, long hStream) Sets device memorySets the memory range of
N8-bit values to the specified valueuc.- Parameters:
dstDevice- destination device pointeruc- value to setN- number of elementshStream- stream identifier
-
cuMemsetD16Async
public static int cuMemsetD16Async(long dstDevice, short us, long N, long hStream) Sets device memorySets the memory range of
N16-bit values to the specified valueus. ThedstDevicepointer must be two byte aligned.- Parameters:
dstDevice- destination device pointerus- value to setN- number of elementshStream- stream identifier
-
cuMemsetD32Async
public static int cuMemsetD32Async(long dstDevice, int ui, long N, long hStream) Sets device memory.Sets the memory range of
N32-bit values to the specified valueui. ThedstDevicepointer must be four byte aligned.- Parameters:
dstDevice- destination device pointerui- value to setN- number of elementshStream- stream identifier
-
cuMemsetD2D8Async
public static int cuMemsetD2D8Async(long dstDevice, long dstPitch, byte uc, long Width, long Height, long hStream) Sets device memory.Sets the 2D memory range of
Width8-bit values to the specified valueuc.Heightspecifies the number of rows to set, anddstPitchspecifies the number of bytes between each row. This function performs fastest when the pitch is one that has been passed back byMemAllocPitch.- Parameters:
dstDevice- destination device pointerdstPitch- pitch of destination device pointer(Unused ifHeightis 1)uc- value to setWidth- width of rowHeight- number of rowshStream- stream identifier
-
cuMemsetD2D16Async
public static int cuMemsetD2D16Async(long dstDevice, long dstPitch, short us, long Width, long Height, long hStream) Sets device memory.Sets the 2D memory range of
Width16-bit values to the specified valueus.Heightspecifies the number of rows to set, anddstPitchspecifies the number of bytes between each row. ThedstDevicepointer anddstPitchoffset must be two byte aligned. This function performs fastest when the pitch is one that has been passed back byMemAllocPitch.- Parameters:
dstDevice- destination device pointerdstPitch- pitch of destination device pointer(Unused ifHeightis 1)us- value to setWidth- width of rowHeight- number of rowshStream- stream identifier
-
cuMemsetD2D32Async
public static int cuMemsetD2D32Async(long dstDevice, long dstPitch, int ui, long Width, long Height, long hStream) Sets device memory.Sets the 2D memory range of
Width32-bit values to the specified valueui.Heightspecifies the number of rows to set, anddstPitchspecifies the number of bytes between each row. ThedstDevicepointer anddstPitchoffset must be four byte aligned. This function performs fastest when the pitch is one that has been passed back byMemAllocPitch.- Parameters:
dstDevice- destination device pointerdstPitch- pitch of destination device pointer(Unused ifHeightis 1)ui- value to setWidth- width of rowHeight- number of rowshStream- stream identifier
-
ncuArrayCreate
public static int ncuArrayCreate(long pHandle, long pAllocateArray) Unsafe version of:ArrayCreate -
cuArrayCreate
Creates a 1D or 2D CUDA array.Creates a CUDA array according to the
CUDA_ARRAY_DESCRIPTORstructurepAllocateArrayand returns a handle to the new CUDA array in*pHandle.- Parameters:
pHandle- returned arraypAllocateArray- array descriptor
-
ncuArrayGetDescriptor
public static int ncuArrayGetDescriptor(long pArrayDescriptor, long hArray) Unsafe version of:ArrayGetDescriptor -
cuArrayGetDescriptor
Get a 1D or 2D CUDA array descriptor.Returns in
*pArrayDescriptora descriptor containing information on the format and dimensions of the CUDA arrayhArray. It is useful for subroutines that have been passed a CUDA array, but need to know the CUDA array parameters for validation or other purposes.- Parameters:
pArrayDescriptor- returned array descriptorhArray- array to get descriptor of
-
ncuArrayGetSparseProperties
public static int ncuArrayGetSparseProperties(long sparseProperties, long array) Unsafe version of:ArrayGetSparseProperties -
cuArrayGetSparseProperties
public static int cuArrayGetSparseProperties(CUDA_ARRAY_SPARSE_PROPERTIES sparseProperties, long array) Returns the layout properties of a sparse CUDA array.Returns the layout properties of a sparse CUDA array in
sparsePropertiesIf the CUDA array is not allocated with flagCUDA_ARRAY3D_SPARSECUDA_ERROR_INVALID_VALUEwill be returned.If the returned value in
CUDA_ARRAY_SPARSE_PROPERTIESflagscontainsARRAY_SPARSE_PROPERTIES_SINGLE_MIPTAIL, thenCUDA_ARRAY_SPARSE_PROPERTIES::miptailSizerepresents the total size of the array. Otherwise, it will be zero. Also, the returned value inCUDA_ARRAY_SPARSE_PROPERTIES::miptailFirstLevelis always zero. Note that thearraymust have been allocated usingArrayCreateorArray3DCreate. For CUDA arrays obtained usingMipmappedArrayGetLevel,CUDA_ERROR_INVALID_VALUEwill be returned. Instead,MipmappedArrayGetSparsePropertiesmust be used to obtain the sparse properties of the entire CUDA mipmapped array to whicharraybelongs to.- Parameters:
sparseProperties- pointer toCUDA_ARRAY_SPARSE_PROPERTIESarray- CUDA array to get the sparse properties of
-
ncuMipmappedArrayGetSparseProperties
public static int ncuMipmappedArrayGetSparseProperties(long sparseProperties, long mipmap) Unsafe version of:MipmappedArrayGetSparseProperties -
cuMipmappedArrayGetSparseProperties
public static int cuMipmappedArrayGetSparseProperties(CUDA_ARRAY_SPARSE_PROPERTIES sparseProperties, long mipmap) Returns the layout properties of a sparse CUDA mipmapped array.Returns the sparse array layout properties in
sparsePropertiesIf the CUDA mipmapped array is not allocated with flagCUDA_ARRAY3D_SPARSECUDA_ERROR_INVALID_VALUEwill be returned.For non-layered CUDA mipmapped arrays,
CUDA_ARRAY_SPARSE_PROPERTIES::miptailSizereturns the size of the mip tail region. The mip tail region includes all mip levels whose width, height or depth is less than that of the tile. For layered CUDA mipmapped arrays, ifCUDA_ARRAY_SPARSE_PROPERTIES::flagscontainsARRAY_SPARSE_PROPERTIES_SINGLE_MIPTAIL, thenCUDA_ARRAY_SPARSE_PROPERTIES::miptailSizespecifies the size of the mip tail of all layers combined. Otherwise,CUDA_ARRAY_SPARSE_PROPERTIES::miptailSizespecifies mip tail size per layer. The returned value ofCUDA_ARRAY_SPARSE_PROPERTIES::miptailFirstLevelis valid only ifCUDA_ARRAY_SPARSE_PROPERTIES::miptailSizeis non-zero.- Parameters:
sparseProperties- pointer toCUDA_ARRAY_SPARSE_PROPERTIESmipmap- CUDA mipmapped array to get the sparse properties of
-
ncuArrayGetPlane
public static int ncuArrayGetPlane(long pPlaneArray, long hArray, int planeIdx) Unsafe version of:ArrayGetPlane -
cuArrayGetPlane
Gets a CUDA array plane from a CUDA array.Returns in
pPlaneArraya CUDA array that represents a single format plane of the CUDA arrayhArray.If
planeIdxis greater than the maximum number of planes in this array or if the array does not have a multi-planar format e.g:AD_FORMAT_NV12, thenCUDA_ERROR_INVALID_VALUEis returned.Note that if the
hArrayhas formatAD_FORMAT_NV12, then passing in 0 forplaneIdxreturns a CUDA array of the same size ashArraybut with one channel andAD_FORMAT_UNSIGNED_INT8as its format. If 1 is passed forplaneIdx, then the returned CUDA array has half the height and width ofhArraywith two channels andAD_FORMAT_UNSIGNED_INT8as its format.- Parameters:
pPlaneArray- returned CUDA array referenced by theplaneIdxhArray- multiplanar CUDA arrayplaneIdx- plane index
-
cuArrayDestroy
public static int cuArrayDestroy(long hArray) Destroys a CUDA array.Destroys the CUDA array
hArray.- Parameters:
hArray- array to destroy
-
ncuArray3DCreate
public static int ncuArray3DCreate(long pHandle, long pAllocateArray) Unsafe version of:Array3DCreate -
cuArray3DCreate
Creates a 3D CUDA array.Creates a CUDA array according to the
CUDA_ARRAY3D_DESCRIPTORstructurepAllocateArrayand returns a handle to the new CUDA array inpHandle.Width,Height, andDepthare the width, height, and depth of the CUDA array (in elements); the following types of CUDA arrays can be allocated:- A 1D array is allocated if
HeightandDepthextents are both zero. - A 2D array is allocated if only
Depthextent is zero. - A 3D array is allocated if all three extents are non-zero.
- A 1D layered CUDA array is allocated if only
Heightis zero and theCUDA_ARRAY3D_LAYEREDflag is set. Each layer is a 1D array. The number of layers is determined by the depth extent. - A 2D layered CUDA array is allocated if all three extents are non-zero and the
CUDA_ARRAY3D_LAYEREDflag is set. Each layer is a 2D array. The number of layers is determined by the depth extent. - A cubemap CUDA array is allocated if all three extents are non-zero and the
CUDA_ARRAY3D_CUBEMAPflag is set.Widthmust be equal toHeight, andDepthmust be six. A cubemap is a special type of 2D layered CUDA array, where the six layers represent the six faces of a cube. The order of the six layers in memory is the same as that listed inCUarray_cubemap_face. - A cubemap layered CUDA array is allocated if all three extents are non-zero, and both,
CUDA_ARRAY3D_CUBEMAPandCUDA_ARRAY3D_LAYEREDflags are set.Widthmust be equal toHeight, andDepthmust be a multiple of six. A cubemap layered CUDA array is a special type of 2D layered CUDA array that consists of a collection of cubemaps. The first six layers represent the first cubemap, the next six layers form the second cubemap, and so on.
- A 1D array is allocated if
Formatspecifies the format of the elements.NumChannelsspecifies the number of packed components per CUDA array element; it may be 1, 2, or 4;Flagsmay be set toCUDA_ARRAY3D_LAYEREDto enable creation of layered CUDA arrays. If this flag is set,Depthspecifies the number of layers, not the depth of a 3D array.CUDA_ARRAY3D_SURFACE_LDSTto enable surface references to be bound to the CUDA array. If this flag is not set,SurfRefSetArraywill fail when attempting to bind the CUDA array to a surface reference.CUDA_ARRAY3D_CUBEMAPto enable creation of cubemaps. If this flag is set,Widthmust be equal toHeight, andDepthmust be six. If theCUDA_ARRAY3D_LAYEREDflag is also set, thenDepthmust be a multiple of six.CUDA_ARRAY3D_TEXTURE_GATHERto indicate that the CUDA array will be used for texture gather. Texture gather can only be performed on 2D CUDA arrays.
Width,HeightandDepthmust meet certain size requirements as listed in the following table. All values are specified in elements. Note that for brevity's sake, the full name of the device attribute is not specified. For ex., TEXTURE1D_WIDTH refers to the device attributeDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH.Note that 2D CUDA arrays have different size requirements if the
CUDA_ARRAY3D_TEXTURE_GATHERflag is set.WidthandHeightmust not be greater thanDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTHandDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHTrespectively, in that case.CUDA array type Valid extents that must always be met
{(width range in elements), (height range), (depth range)}Valid extents with CUDA_ARRAY3D_SURFACE_LDST set
{(width range in elements), (height range), (depth range)}1D { (1,TEXTURE1D_WIDTH), 0, 0 } { (1,SURFACE1D_WIDTH), 0, 0 } 2D { (1,TEXTURE2D_WIDTH), (1,TEXTURE2D_HEIGHT), 0 } { (1,SURFACE2D_WIDTH), (1,SURFACE2D_HEIGHT), 0 } 3D { (1,TEXTURE3D_WIDTH), (1,TEXTURE3D_HEIGHT), (1,TEXTURE3D_DEPTH) }
OR
{ (1,TEXTURE3D_WIDTH_ALTERNATE), (1,TEXTURE3D_HEIGHT_ALTERNATE), (1,TEXTURE3D_DEPTH_ALTERNATE) }{ (1,SURFACE3D_WIDTH), (1,SURFACE3D_HEIGHT), (1,SURFACE3D_DEPTH) } 1D Layered { (1,TEXTURE1D_LAYERED_WIDTH), 0, (1,TEXTURE1D_LAYERED_LAYERS) } { (1,SURFACE1D_LAYERED_WIDTH), 0, (1,SURFACE1D_LAYERED_LAYERS) } 2D Layered { (1,TEXTURE2D_LAYERED_WIDTH), (1,TEXTURE2D_LAYERED_HEIGHT), (1,TEXTURE2D_LAYERED_LAYERS) } { (1,SURFACE2D_LAYERED_WIDTH), (1,SURFACE2D_LAYERED_HEIGHT), (1,SURFACE2D_LAYERED_LAYERS) } Cubemap { (1,TEXTURECUBEMAP_WIDTH), (1,TEXTURECUBEMAP_WIDTH), 6 } { (1,SURFACECUBEMAP_WIDTH), (1,SURFACECUBEMAP_WIDTH), 6 } Cubemap Layered { (1,TEXTURECUBEMAP_LAYERED_WIDTH), (1,TEXTURECUBEMAP_LAYERED_WIDTH), (1,TEXTURECUBEMAP_LAYERED_LAYERS) } { (1,SURFACECUBEMAP_LAYERED_WIDTH), (1,SURFACECUBEMAP_LAYERED_WIDTH), (1,SURFACECUBEMAP_LAYERED_LAYERS) } - Parameters:
pHandle- returned arraypAllocateArray- 3D array descriptor
-
ncuArray3DGetDescriptor
public static int ncuArray3DGetDescriptor(long pArrayDescriptor, long hArray) Unsafe version of:Array3DGetDescriptor -
cuArray3DGetDescriptor
Get a 3D CUDA array descriptor.Returns in
*pArrayDescriptora descriptor containing information on the format and dimensions of the CUDA arrayhArray. It is useful for subroutines that have been passed a CUDA array, but need to know the CUDA array parameters for validation or other purposes.This function may be called on 1D and 2D arrays, in which case the
Heightand/orDepthmembers of the descriptor struct will be set to 0.- Parameters:
pArrayDescriptor- returned 3D array descriptorhArray- 3D array to get descriptor of
-
ncuMipmappedArrayCreate
public static int ncuMipmappedArrayCreate(long pHandle, long pMipmappedArrayDesc, int numMipmapLevels) Unsafe version of:MipmappedArrayCreate -
cuMipmappedArrayCreate
public static int cuMipmappedArrayCreate(PointerBuffer pHandle, CUDA_ARRAY3D_DESCRIPTOR pMipmappedArrayDesc, int numMipmapLevels) Creates a CUDA mipmapped array.Creates a CUDA mipmapped array according to the
CUDA_ARRAY3D_DESCRIPTORstructurepMipmappedArrayDescand returns a handle to the new CUDA mipmapped array in*pHandle.numMipmapLevelsspecifies the number of mipmap levels to be allocated. This value is clamped to the range[1, 1 + floor(log2(max(width, height, depth)))].Width,Height, andDepthare the width, height, and depth of the CUDA array (in elements); the following types of CUDA arrays can be allocated:- A 1D mipmapped array is allocated if
HeightandDepthextents are both zero. - A 2D mipmapped array is allocated if only
Depthextent is zero. - A 3D mipmapped array is allocated if all three extents are non-zero.
- A 1D layered CUDA mipmapped array is allocated if only
Heightis zero and theCUDA_ARRAY3D_LAYEREDflag is set. Each layer is a 1D array. The number of layers is determined by the depth extent. - A 2D layered CUDA mipmapped array is allocated if all three extents are non-zero and the
CUDA_ARRAY3D_LAYEREDflag is set. Each layer is a 2D array. The number of layers is determined by the depth extent. - A cubemap CUDA mipmapped array is allocated if all three extents are non-zero and the
CUDA_ARRAY3D_CUBEMAPflag is set.Widthmust be equal toHeight, andDepthmust be six. A cubemap is a special type of 2D layered CUDA array, where the six layers represent the six faces of a cube. The order of the six layers in memory is the same as that listed inCUarray_cubemap_face. - A cubemap layered CUDA mipmapped array is allocated if all three extents are non-zero, and both,
CUDA_ARRAY3D_CUBEMAPandCUDA_ARRAY3D_LAYEREDflags are set.Widthmust be equal toHeight, andDepthmust be a multiple of six. A cubemap layered CUDA array is a special type of 2D layered CUDA array that consists of a collection of cubemaps. The first six layers represent the first cubemap, the next six layers form the second cubemap, and so on.
- A 1D mipmapped array is allocated if
Formatspecifies the format of the elements.NumChannelsspecifies the number of packed components per CUDA array element; it may be 1, 2, or 4;- Flags may be set to:
CUDA_ARRAY3D_LAYEREDto enable creation of layered CUDA mipmapped arrays. If this flag is set,Depthspecifies the number of layers, not the depth of a 3D array.CUDA_ARRAY3D_SURFACE_LDSTto enable surface references to be bound to individual mipmap levels of the CUDA mipmapped array. If this flag is not set,SurfRefSetArraywill fail when attempting to bind a mipmap level of the CUDA mipmapped array to a surface reference.CUDA_ARRAY3D_CUBEMAPto enable creation of mipmapped cubemaps. If this flag is set,Widthmust be equal toHeight, andDepthmust be six. If theCUDA_ARRAY3D_LAYEREDflag is also set, thenDepthmust be a multiple of six.CUDA_ARRAY3D_TEXTURE_GATHERto indicate that the CUDA mipmapped array will be used for texture gather. Texture gather can only be performed on 2D CUDA mipmapped arrays.
Width,HeightandDepthmust meet certain size requirements as listed in the following table. All values are specified in elements. Note that for brevity's sake, the full name of the device attribute is not specified. For ex.,TEXTURE1D_MIPMAPPED_WIDTHrefers to the device attributeDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH.CUDA array type Valid extents that must always be met
{(width range in elements), (height range), (depth range)}Valid extents with CUDA_ARRAY3D_SURFACE_LDST set
{(width range in elements), (height range), (depth range)}1D { (1,TEXTURE1D_MIPMAPPED_WIDTH), 0, 0 } { (1,SURFACE1D_WIDTH), 0, 0 } 2D { (1,TEXTURE2D_MIPMAPPED_WIDTH), (1,TEXTURE2D_MIPMAPPED_HEIGHT), 0 } { (1,SURFACE2D_WIDTH), (1,SURFACE2D_HEIGHT), 0 } 3D { (1,TEXTURE3D_WIDTH), (1,TEXTURE3D_HEIGHT), (1,TEXTURE3D_DEPTH) }
OR
{ (1,TEXTURE3D_WIDTH_ALTERNATE), (1,TEXTURE3D_HEIGHT_ALTERNATE), (1,TEXTURE3D_DEPTH_ALTERNATE) }{ (1,SURFACE3D_WIDTH), (1,SURFACE3D_HEIGHT), (1,SURFACE3D_DEPTH) } 1D Layered { (1,TEXTURE1D_LAYERED_WIDTH), 0, (1,TEXTURE1D_LAYERED_LAYERS) } { (1,SURFACE1D_LAYERED_WIDTH), 0, (1,SURFACE1D_LAYERED_LAYERS) } 2D Layered { (1,TEXTURE2D_LAYERED_WIDTH), (1,TEXTURE2D_LAYERED_HEIGHT), (1,TEXTURE2D_LAYERED_LAYERS) } { (1,SURFACE2D_LAYERED_WIDTH), (1,SURFACE2D_LAYERED_HEIGHT), (1,SURFACE2D_LAYERED_LAYERS) } Cubemap { (1,TEXTURECUBEMAP_WIDTH), (1,TEXTURECUBEMAP_WIDTH), 6 } { (1,SURFACECUBEMAP_WIDTH), (1,SURFACECUBEMAP_WIDTH), 6 } Cubemap Layered { (1,TEXTURECUBEMAP_LAYERED_WIDTH), (1,TEXTURECUBEMAP_LAYERED_WIDTH), (1,TEXTURECUBEMAP_LAYERED_LAYERS) } { (1,SURFACECUBEMAP_LAYERED_WIDTH), (1,SURFACECUBEMAP_LAYERED_WIDTH), (1,SURFACECUBEMAP_LAYERED_LAYERS) } - Parameters:
pHandle- returned mipmapped arraypMipmappedArrayDesc- mipmapped array descriptornumMipmapLevels- number of mipmap levels
-
ncuMipmappedArrayGetLevel
public static int ncuMipmappedArrayGetLevel(long pLevelArray, long hMipmappedArray, int level) Unsafe version of:MipmappedArrayGetLevel -
cuMipmappedArrayGetLevel
public static int cuMipmappedArrayGetLevel(PointerBuffer pLevelArray, long hMipmappedArray, int level) Gets a mipmap level of a CUDA mipmapped array.Returns in
*pLevelArraya CUDA array that represents a single mipmap level of the CUDA mipmapped arrayhMipmappedArray.If
levelis greater than the maximum number of levels in this mipmapped array,CUDA_ERROR_INVALID_VALUEis returned.- Parameters:
pLevelArray- returned mipmap level CUDA arrayhMipmappedArray- CUDA mipmapped arraylevel- mipmap level
-
cuMipmappedArrayDestroy
public static int cuMipmappedArrayDestroy(long hMipmappedArray) Destroys a CUDA mipmapped array.Destroys the CUDA mipmapped array
hMipmappedArray.- Parameters:
hMipmappedArray- mipmapped array to destroy
-
ncuMemAddressReserve
public static int ncuMemAddressReserve(long ptr, long size, long alignment, long addr, long flags) Unsafe version of:MemAddressReserve -
cuMemAddressReserve
public static int cuMemAddressReserve(PointerBuffer ptr, long size, long alignment, long addr, long flags) Allocate an address range reservation.Reserves a virtual address range based on the given parameters, giving the starting address of the range in
ptr. This API requires a system that supports UVA. The size and address parameters must be a multiple of the host page size and the alignment must be a power of two or zero for default alignment.- Parameters:
ptr- resulting pointer to start of virtual address range allocatedsize- size of the reserved virtual address range requestedalignment- alignment of the reserved virtual address range requestedaddr- fixed starting address range requestedflags- currently unused, must be zero
-
cuMemAddressFree
public static int cuMemAddressFree(long ptr, long size) Free an address range reservation.Frees a virtual address range reserved by
MemAddressReserve. The size must match what was given tomemAddressReserveand the ptr given must match what was returned frommemAddressReserve.- Parameters:
ptr- starting address of the virtual address range to freesize- size of the virtual address region to free
-
ncuMemCreate
public static int ncuMemCreate(long handle, long size, long prop, long flags) Unsafe version of:MemCreate -
cuMemCreate
Create a CUDA memory handle representing a memory allocation of a given size described by the given properties.This creates a memory allocation on the target device specified through the
propstrcuture. The created allocation will not have any device or host mappings. The generic memoryhandlefor the allocation can be mapped to the address space of calling process viaMemMap. This handle cannot be transmitted directly to other processes (seeMemExportToShareableHandle). On Windows, the caller must also pass anLPSECURITYATTRIBUTEinpropto be associated with this handle which limits or allows access to this handle for a recepient process (seeCUmemAllocationProp::win32HandleMetaDatafor more). Thesizeof this allocation must be a multiple of the the value given viaMemGetAllocationGranularitywith theMEM_ALLOC_GRANULARITY_MINIMUMflag. IfCUmemAllocationProp::allocFlags::usagecontainsMEM_CREATE_USAGE_TILE_POOLflag then the memory allocation is intended only to be used as backing tile pool for sparse CUDA arrays and sparse CUDA mipmapped arrays. (seeMemMapArrayAsync).- Parameters:
handle- value of handle returned. All operations on this allocation are to be performed using this handle.size- size of the allocation requestedprop- properties of the allocation to createflags- flags for future use, must be zero now
-
cuMemRelease
public static int cuMemRelease(long handle) Release a memory handle representing a memory allocation which was previously allocated throughMemCreate.Frees the memory that was allocated on a device through
cuMemCreate.The memory allocation will be freed when all outstanding mappings to the memory are unmapped and when all outstanding references to the handle (including it's shareable counterparts) are also released. The generic memory handle can be freed when there are still outstanding mappings made with this handle. Each time a recepient process imports a shareable handle, it needs to pair it with
MemReleasefor the handle to be freed. Ifhandleis not a valid handle the behavior is undefined.- Parameters:
handle- value of handle which was returned previously bycuMemCreate
-
cuMemMap
public static int cuMemMap(long ptr, long size, long offset, long handle, long flags) Maps an allocation handle to a reserved virtual address range.Maps bytes of memory represented by
handlestarting from byteoffsettosizeto address range [addr,addr+size]. This range must be an address reservation previously reserved withMemAddressReserve, andoffset+sizemust be less than the size of the memory allocation. Bothptr,size, andoffsetmust be a multiple of the value given viaMemGetAllocationGranularitywith theMEM_ALLOC_GRANULARITY_MINIMUMflag.Please note calling
MemMapdoes not make the address accessible, the caller needs to update accessibility of a contiguous mapped VA range by callingMemSetAccess.Once a recipient process obtains a shareable memory handle from
MemImportFromShareableHandle, the process must useMemMapto map the memory into its address ranges before setting accessibility withMemSetAccess.MemMapcan only create mappings on VA range reservations that are not currently mapped.- Parameters:
ptr- address where memory will be mappedsize- size of the memory mappingoffset- offset into the memory represented by -handlefrom which to start mapping - Note: currently must be zerohandle- handle to a shareable memoryflags- flags for future use, must be zero now
-
ncuMemMapArrayAsync
public static int ncuMemMapArrayAsync(long mapInfoList, int count, long hStream) Unsafe version of:MemMapArrayAsync- Parameters:
count- count ofCUarrayMapInfoinmapInfoList
-
cuMemMapArrayAsync
Maps or unmaps subregions of sparse CUDA arrays and sparse CUDA mipmapped arrays.Performs map or unmap operations on subregions of sparse CUDA arrays and sparse CUDA mipmapped arrays. Each operation is specified by a
CUarrayMapInfoentry in themapInfoListarray of sizecount.where
CUarrayMapInfo::resourceTypespecifies the type of resource to be operated on. IfCUarrayMapInfo::resourceTypeis set toRESOURCE_TYPE_ARRAYthenCUarrayMapInfo::resource::arraymust be set to a valid sparse CUDA array handle. The CUDA array must be either a 2D, 2D layered or 3D CUDA array and must have been allocated usingArrayCreateorArray3DCreatewith the flagCUDA_ARRAY3D_SPARSE. For CUDA arrays obtained usingMipmappedArrayGetLevel,CUDA_ERROR_INVALID_VALUEwill be returned. IfCUarrayMapInfo::resourceTypeis set toRESOURCE_TYPE_MIPMAPPED_ARRAYthenCUarrayMapInfo::resource::mipmapmust be set to a valid sparse CUDA mipmapped array handle. The CUDA mipmapped array must be either a 2D, 2D layered or 3D CUDA mipmapped array and must have been allocated usingMipmappedArrayCreatewith the flagCUDA_ARRAY3D_SPARSE.CUarrayMapInfo::subresourceTypespecifies the type of subresource within the resource.where
ARRAY_SPARSE_SUBRESOURCE_TYPE_SPARSE_LEVELindicates a sparse-miplevel which spans at least one tile in every dimension. The remaining miplevels which are too small to span at least one tile in any dimension constitute the mip tail region as indicated byARRAY_SPARSE_SUBRESOURCE_TYPE_MIPTAILsubresource type.If
CUarrayMapInfo::subresourceTypeis set toARRAY_SPARSE_SUBRESOURCE_TYPE_SPARSE_LEVELthenCUarrayMapInfo::subresource::sparseLevelstruct must contain valid array subregion offsets and extents. TheCUarrayMapInfo::subresource::sparseLevel::offsetX,CUarrayMapInfo::subresource::sparseLevel::offsetYandCUarrayMapInfo::subresource::sparseLevel::offsetZmust specify valid X, Y and Z offsets respectively. TheCUarrayMapInfo::subresource::sparseLevel::extentWidth,CUarrayMapInfo::subresource::sparseLevel::extentHeightandCUarrayMapInfo::subresource::sparseLevel::extentDepthmust specify valid width, height and depth extents respectively. These offsets and extents must be aligned to the corresponding tile dimension. For CUDA mipmapped arraysCUarrayMapInfo::subresource::sparseLevel::levelmust specify a valid mip level index. Otherwise, must be zero. For layered CUDA arrays and layered CUDA mipmapped arraysCUarrayMapInfo::subresource::sparseLevel::layermust specify a valid layer index. Otherwise, must be zero.CUarrayMapInfo::subresource::sparseLevel::offsetZmust be zero andCUarrayMapInfo::subresource::sparseLevel::extentDepthmust be set to 1 for 2D and 2D layered CUDA arrays and CUDA mipmapped arrays. Tile extents can be obtained by callingArrayGetSparsePropertiesandMipmappedArrayGetSparsePropertiesIf
CUarrayMapInfo::subresourceTypeis set toARRAY_SPARSE_SUBRESOURCE_TYPE_MIPTAILthenCUarrayMapInfo::subresource::miptailstruct must contain valid mip tail offset inCUarrayMapInfo::subresource::miptail::offsetand size inCUarrayMapInfo::subresource::miptail::size. Both, mip tail offset and mip tail size must be aligned to the tile size. For layered CUDA mipmapped arrays which don't have the flagARRAY_SPARSE_PROPERTIES_SINGLE_MIPTAILset inCUDA_ARRAY_SPARSE_PROPERTIES::flagsas returned byMipmappedArrayGetSparseProperties,CUarrayMapInfo::subresource::miptail::layermust specify a valid layer index. Otherwise, must be zero.CUarrayMapInfo::memOperationTypespecifies the type of operation.If
CUarrayMapInfo::memOperationTypeis set toMEM_OPERATION_TYPE_MAPthen the subresource will be mapped onto the tile pool memory specified byCUarrayMapInfo::memHandleat offsetCUarrayMapInfo::offset. The tile pool allocation has to be created by specifying theMEM_CREATE_USAGE_TILE_POOLflag when callingMemCreate. Also,CUarrayMapInfo::memHandleTypemust be set toMEM_HANDLE_TYPE_GENERIC.If
CUarrayMapInfo::memOperationTypeis set toMEM_OPERATION_TYPE_UNMAPthen an unmapping operation is performed.CUarrayMapInfo::memHandlemust be NULL.CUarrayMapInfo::deviceBitMaskspecifies the list of devices that must map or unmap physical memory. Currently, this mask must have exactly one bit set, and the corresponding device must match the device associated with the stream. IfCUarrayMapInfo::memOperationTypeis set toMEM_OPERATION_TYPE_MAP, the device must also match the device associated with the tile pool memory allocation as specified byCUarrayMapInfo::memHandle.CUarrayMapInfo::flagsandCUarrayMapInfo::reserved[]are unused and must be set to zero.- Parameters:
mapInfoList- list ofCUarrayMapInfohStream- stream identifier for the stream to use for map or unmap operations
-
cuMemUnmap
public static int cuMemUnmap(long ptr, long size) Unmap the backing memory of a given address range.The range must be the entire contiguous address range that was mapped to. In other words,
MemUnmapcannot unmap a sub-range of an address range mapped byMemCreate/MemMap. Any backing memory allocations will be freed if there are no existing mappings and there are no unreleased memory handles.When
MemUnmapreturns successfully the address range is converted to an address reservation and can be used for a future calls toMemMap. Any new mapping to this virtual address will need to have access granted throughMemSetAccess, as all mappings start with no accessibility setup.- Parameters:
ptr- starting address for the virtual address range to unmapsize- size of the virtual address range to unmap
-
ncuMemSetAccess
public static int ncuMemSetAccess(long ptr, long size, long desc, long count) Unsafe version of:MemSetAccess- Parameters:
count- number ofCUmemAccessDescindesc
-
cuMemSetAccess
Set the access flags for each location specified indescfor the given virtual address range.Given the virtual address range via
ptrandsize, and the locations in the array given bydescandcount, set the access flags for the target locations. The range must be a fully mapped address range containing all allocations created byMemMap/MemCreate.- Parameters:
ptr- starting address for the virtual address rangesize- length of the virtual address rangedesc- array ofCUmemAccessDescthat describe how to change the - mapping for each location specified
-
ncuMemGetAccess
public static int ncuMemGetAccess(long flags, long location, long ptr) Unsafe version of:MemGetAccess -
cuMemGetAccess
Get the accessflagsset for the givenlocationandptr.- Parameters:
flags- flags set for this locationlocation- location in which to check the flags forptr- address in which to check the access flags for
-
ncuMemGetAllocationGranularity
public static int ncuMemGetAllocationGranularity(long granularity, long prop, int option) Unsafe version of:MemGetAllocationGranularity -
cuMemGetAllocationGranularity
public static int cuMemGetAllocationGranularity(PointerBuffer granularity, CUmemAllocationProp prop, int option) Calculates either the minimal or recommended granularity.Calculates either the minimal or recommended granularity for a given allocation specification and returns it in granularity. This granularity can be used as a multiple for alignment, size, or address mapping.
- Parameters:
granularity- returned granularityprop- property for which to determine the granularity foroption- determines which granularity to return
-
ncuMemGetAllocationPropertiesFromHandle
public static int ncuMemGetAllocationPropertiesFromHandle(long prop, long handle) Unsafe version of:MemGetAllocationPropertiesFromHandle -
cuMemGetAllocationPropertiesFromHandle
Retrieve the contents of the property structure defining properties for this handle.- Parameters:
prop- pointer to a properties structure which will hold the information about this handlehandle- handle which to perform the query on
-
ncuMemRetainAllocationHandle
public static int ncuMemRetainAllocationHandle(long handle, long addr) Unsafe version of:MemRetainAllocationHandle -
cuMemRetainAllocationHandle
Given an addressaddr, returns the allocation handle of the backing memory allocation.The handle is guaranteed to be the same handle value used to map the memory. If the address requested is not mapped, the function will fail. The returned handle must be released with corresponding number of calls to
MemRelease.Note
The address
addr, can be any address in a range previously mapped byMemMap, and not necessarily the start address.- Parameters:
handle- CUDA Memory handle for the backing memory allocationaddr- memory address to query, that has been mapped previously
-
cuMemFreeAsync
public static int cuMemFreeAsync(long dptr, long hStream) Frees memory with stream ordered semantics.Inserts a free operation into
hStream. The allocation must not be accessed after stream execution reaches the free. After this API returns, accessing the memory from any subsequent work launched on the GPU or querying its pointer attributes results in undefined behavior.Note
During stream capture, this function results in the creation of a free node and must therefore be passed the address of a graph allocation.
- Parameters:
dptr- memory to freehStream- the stream establishing the stream ordering contract
-
ncuMemAllocAsync
public static int ncuMemAllocAsync(long dptr, long bytesize, long hStream) Unsafe version of:MemAllocAsync -
cuMemAllocAsync
Allocates memory with stream ordered semanticsInserts an allocation operation into
hStream. A pointer to the allocated memory is returned immediately in*dptr. The allocation must not be accessed until the the allocation operation completes. The allocation comes from the memory pool current to the stream's device.Note
The default memory pool of a device contains device memory from that device.
Note
Basic stream ordering allows future work submitted into the same stream to use the allocation. Stream query, stream synchronize, and CUDA events can be used to guarantee that the allocation operation completes before work submitted in a separate stream runs.
Note
During stream capture, this function results in the creation of an allocation node. In this case, the allocation is owned by the graph instead of the memory pool. The memory pool's properties are used to set the node's creation parameters.
- Parameters:
dptr- returned device pointerbytesize- number of bytes to allocatehStream- the stream establishing the stream ordering contract and the memory pool to allocate from
-
cuMemPoolTrimTo
public static int cuMemPoolTrimTo(long pool, long minBytesToKeep) Tries to release memory back to the OS.Releases memory back to the OS until the pool contains fewer than
minBytesToKeepreserved bytes, or there is no more memory that the allocator can safely release. The allocator cannot release OS allocations that back outstanding asynchronous allocations. The OS allocations may happen at different granularity from the user allocations.Note
Allocations that have not been freed count as outstanding.
Note
Allocations that have been asynchronously freed but whose completion has not been observed on the host (eg. by a synchronize) can count as outstanding.
- Parameters:
pool- the memory pool to trimminBytesToKeep- if the pool has less thanminBytesToKeepreserved, theTrimTooperation is a no-op. Otherwise the pool will be guaranteed to have at leastminBytesToKeepbytes reserved after the operation.
-
ncuMemPoolSetAttribute
public static int ncuMemPoolSetAttribute(long pool, int attr, long value) Unsafe version of:MemPoolSetAttribute -
cuMemPoolSetAttribute
Sets attributes of a memory pool.- Parameters:
pool- the memory pool to modifyattr- the attribute to modify. One of:value- pointer to the value to assign
-
cuMemPoolSetAttribute
Sets attributes of a memory pool.- Parameters:
pool- the memory pool to modifyattr- the attribute to modify. One of:value- pointer to the value to assign
-
cuMemPoolSetAttribute
Sets attributes of a memory pool.- Parameters:
pool- the memory pool to modifyattr- the attribute to modify. One of:value- pointer to the value to assign
-
ncuMemPoolGetAttribute
public static int ncuMemPoolGetAttribute(long pool, int attr, long value) Unsafe version of:MemPoolGetAttribute -
cuMemPoolGetAttribute
Gets attributes of a memory pool.- Parameters:
pool- the memory pool to get attributes ofattr- the attribute to get. One of:value- retrieved value
-
cuMemPoolGetAttribute
Gets attributes of a memory pool.- Parameters:
pool- the memory pool to get attributes ofattr- the attribute to get. One of:value- retrieved value
-
cuMemPoolGetAttribute
Gets attributes of a memory pool.- Parameters:
pool- the memory pool to get attributes ofattr- the attribute to get. One of:value- retrieved value
-
ncuMemPoolSetAccess
public static int ncuMemPoolSetAccess(long pool, long map, long count) Unsafe version of:MemPoolSetAccess- Parameters:
count- number of descriptors in the map array
-
cuMemPoolSetAccess
Controls visibility of pools between devices.- Parameters:
pool- the pool being modifiedmap- array of access descriptors. Each descriptor instructs the access to enable for a single gpu.
-
ncuMemPoolGetAccess
public static int ncuMemPoolGetAccess(long flags, long memPool, long location) Unsafe version of:MemPoolGetAccess -
cuMemPoolGetAccess
Returns the accessibility of a pool from a device.Returns the accessibility of the pool's memory from the specified location.
- Parameters:
flags- the accessibility of the pool from the specified locationmemPool- the pool being queriedlocation- the location accessing the pool
-
ncuMemPoolCreate
public static int ncuMemPoolCreate(long pool, long poolProps) Unsafe version of:MemPoolCreate -
cuMemPoolCreate
Creates a memory pool.Creates a CUDA memory pool and returns the handle in
pool. ThepoolPropsdetermines the properties of the pool such as the backing device and IPC capabilities.By default, the pool's memory will be accessible from the device it is allocated on.
Note
Specifying
MEM_HANDLE_TYPE_NONEcreates a memory pool that will not support IPC. -
cuMemPoolDestroy
public static int cuMemPoolDestroy(long pool) Destroys the specified memory pool.If any pointers obtained from this pool haven't been freed or the pool has free operations that haven't completed when
MemPoolDestroyis invoked, the function will return immediately and the resources associated with the pool will be released automatically once there are no more outstanding allocations.Destroying the current mempool of a device sets the default mempool of that device as the current mempool for that device.
Note
A device's default memory pool cannot be destroyed.
-
ncuMemAllocFromPoolAsync
public static int ncuMemAllocFromPoolAsync(long dptr, long bytesize, long pool, long hStream) Unsafe version of:MemAllocFromPoolAsync -
cuMemAllocFromPoolAsync
public static int cuMemAllocFromPoolAsync(PointerBuffer dptr, long bytesize, long pool, long hStream) Allocates memory from a specified pool with stream ordered semantics.Inserts an allocation operation into
hStream. A pointer to the allocated memory is returned immediately in*dptr. The allocation must not be accessed until the the allocation operation completes. The allocation comes from the specified memory pool.Note
The specified memory pool may be from a device different than that of the specified
hStream.- Basic stream ordering allows future work submitted into the same stream to use the allocation. Stream query, stream synchronize, and CUDA events can be used to guarantee that the allocation operation completes before work submitted in a separate stream runs.
Note
During stream capture, this function results in the creation of an allocation node. In this case, the allocation is owned by the graph instead of the memory pool. The memory pool's properties are used to set the node's creation parameters.
- Parameters:
dptr- returned device pointerbytesize- number of bytes to allocatepool- the pool to allocate fromhStream- the stream establishing the stream ordering semantic
-
ncuMemPoolExportPointer
public static int ncuMemPoolExportPointer(long shareData_out, long ptr) Unsafe version of:MemPoolExportPointer -
cuMemPoolExportPointer
Export data to share a memory pool allocation between processes.Constructs
shareData_outfor sharing a specific allocation from an already shared memory pool. The recipient process can import the allocation with theMemPoolImportPointerapi. The data is not a handle and may be shared through any IPC mechanism.- Parameters:
shareData_out- returned export dataptr- pointer to memory being exported
-
ncuMemPoolImportPointer
public static int ncuMemPoolImportPointer(long ptr_out, long pool, long shareData) Unsafe version of:MemPoolImportPointer -
cuMemPoolImportPointer
public static int cuMemPoolImportPointer(PointerBuffer ptr_out, long pool, CUmemPoolPtrExportData shareData) Import a memory pool allocation from another process.Returns in
ptr_outa pointer to the imported memory. The imported memory must not be accessed before the allocation operation completes in the exporting process. The imported memory must be freed from all importing processes before being freed in the exporting process. The pointer may be freed withMemFreeorMemFreeAsync. IfcuMemFreeAsyncis used, the free must be completed on the importing process before the free operation on the exporting process.Note
The
cuMemFreeAsyncapi may be used in the exporting process before the cuMemFreeAsync operation completes in its stream as long as thecuMemFreeAsyncin the exporting process specifies a stream with a stream dependency on the importing process'scuMemFreeAsync.- Parameters:
ptr_out- pointer to imported memorypool- pool from which to importshareData- data specifying the memory to import
-
ncuPointerGetAttribute
public static int ncuPointerGetAttribute(long data, int attribute, long ptr) Unsafe version of:PointerGetAttribute -
cuPointerGetAttribute
Returns information about a pointer.The supported attributes are:
POINTER_ATTRIBUTE_CONTEXT: Returns in*datatheCUcontextin whichptrwas allocated or registered. The type ofdatamust beCUcontext *.If
ptrwas not allocated by, mapped by, or registered with aCUcontextwhich uses unified virtual addressing thenCUDA_ERROR_INVALID_VALUEis returned.POINTER_ATTRIBUTE_MEMORY_TYPE:Returns in
*datathe physical memory type of the memory thatptraddresses as aCUmemorytypeenumerated value. The type ofdatamust be unsigned int.If
ptraddresses device memory then*datais set toMEMORYTYPE_DEVICE. The particularCUdeviceon which the memory resides is theCUdeviceof theCUcontextreturned by thePOINTER_ATTRIBUTE_CONTEXTattribute ofptr.If
ptraddresses host memory then*datais set toMEMORYTYPE_HOST.If
ptrwas not allocated by, mapped by, or registered with aCUcontextwhich uses unified virtual addressing thenCUDA_ERROR_INVALID_VALUEis returned.If the current
CUcontextdoes not support unified virtual addressing thenCUDA_ERROR_INVALID_CONTEXTis returned.POINTER_ATTRIBUTE_DEVICE_POINTER: Returns in*datathe device pointer value through whichptrmay be accessed by kernels running in the currentCUcontext. The type ofdatamust beCUdeviceptr *.If there exists no device pointer value through which kernels running in the current
CUcontextmay accessptrthenCUDA_ERROR_INVALID_VALUEis returned.If there is no current
CUcontextthenCUDA_ERROR_INVALID_CONTEXTis returned.Except in the exceptional disjoint addressing cases discussed below, the value returned in
*datawill equal the input valueptr.POINTER_ATTRIBUTE_HOST_POINTER: Returns in*datathe host pointer value through whichptrmay be accessed by by the host program. The type ofdatamust bevoid **. If there exists no host pointer value through which the host program may directly accessptrthenCUDA_ERROR_INVALID_VALUEis returned.Except in the exceptional disjoint addressing cases discussed below, the value returned in
*datawill equal the input valueptr.POINTER_ATTRIBUTE_P2P_TOKENS: Returns in*datatwo tokens for use with the nv-p2p.h Linux kernel interface.datamust be a struct of typeCUDA_POINTER_ATTRIBUTE_P2P_TOKENS.ptrmust be a pointer to memory obtained fromMemAlloc. Note thatp2pTokenandvaSpaceTokenare only valid for the lifetime of the source allocation. A subsequent allocation at the same address may return completely different tokens. Querying this attribute has a side effect of setting the attributePOINTER_ATTRIBUTE_SYNC_MEMOPSfor the region of memory thatptrpoints to.POINTER_ATTRIBUTE_SYNC_MEMOPS:A boolean attribute which when set, ensures that synchronous memory operations initiated on the region of memory that
ptrpoints to will always synchronize. See further documentation in the section titled "API synchronization behavior" to learn more about cases when synchronous memory operations can exhibit asynchronous behavior.POINTER_ATTRIBUTE_BUFFER_ID: Returns in*dataa buffer ID which is guaranteed to be unique within the process.datamust point to an unsigned long long.ptrmust be a pointer to memory obtained from a CUDA memory allocation API. Every memory allocation from any of the CUDA memory allocation APIs will have a unique ID over a process lifetime. Subsequent allocations do not reuse IDs from previous freed allocations. IDs are only unique within a single process.POINTER_ATTRIBUTE_IS_MANAGED: Returns in*dataa boolean that indicates whether the pointer points to managed memory or not.If
ptris not a valid CUDA pointer thenCUDA_ERROR_INVALID_VALUEis returned.POINTER_ATTRIBUTE_DEVICE_ORDINAL: Returns in*dataan integer representing a device ordinal of a device against which the memory was allocated or registered.POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE: Returns in*dataa boolean that indicates if this pointer maps to an allocation that is suitable forcudaIpcGetMemHandle().POINTER_ATTRIBUTE_RANGE_START_ADDR: Returns in*datathe starting address for the allocation referenced by the device pointerptr. Note that this is not necessarily the address of the mapped region, but the address of the mappable address rangeptrreferences (e.g. fromMemAddressReserve).POINTER_ATTRIBUTE_RANGE_SIZE: Returns in*datathe size for the allocation referenced by the device pointerptr. Note that this is not necessarily the size of the mapped region, but the size of the mappable address rangeptrreferences (e.g. fromMemAddressReserve). To retrieve the size of the mapped region, seeMemGetAddressRange.POINTER_ATTRIBUTE_MAPPED: Returns in*dataa boolean that indicates if this pointer is in a valid address range that is mapped to a backing allocation.POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES: Returns a bitmask of the allowed handle types for an allocation that may be passed toMemExportToShareableHandle.POINTER_ATTRIBUTE_MEMPOOL_HANDLE: Returns in*datathe handle to the mempool that the allocation was obtained from.
Note that for most allocations in the unified virtual address space the host and device pointer for accessing the allocation will be the same. The exceptions to this are - user memory registered using
MemHostRegister- host memory allocated usingMemHostAllocwith theMEMHOSTALLOC_WRITECOMBINEDflag For these types of allocation there will exist separate, disjoint host and device addresses for accessing the allocation. In particular- The host address will correspond to an invalid unmapped device address (which will result in an exception if accessed from the device)
- The device address will correspond to an invalid unmapped host address (which will result in an exception if accessed from the host).
For these types of allocations, querying
POINTER_ATTRIBUTE_HOST_POINTERandPOINTER_ATTRIBUTE_DEVICE_POINTERmay be used to retrieve the host and device addresses from either address.- Parameters:
data- returned pointer attribute valueattribute- pointer attribute to queryptr- pointer
-
cuPointerGetAttribute
Returns information about a pointer.The supported attributes are:
POINTER_ATTRIBUTE_CONTEXT: Returns in*datatheCUcontextin whichptrwas allocated or registered. The type ofdatamust beCUcontext *.If
ptrwas not allocated by, mapped by, or registered with aCUcontextwhich uses unified virtual addressing thenCUDA_ERROR_INVALID_VALUEis returned.POINTER_ATTRIBUTE_MEMORY_TYPE:Returns in
*datathe physical memory type of the memory thatptraddresses as aCUmemorytypeenumerated value. The type ofdatamust be unsigned int.If
ptraddresses device memory then*datais set toMEMORYTYPE_DEVICE. The particularCUdeviceon which the memory resides is theCUdeviceof theCUcontextreturned by thePOINTER_ATTRIBUTE_CONTEXTattribute ofptr.If
ptraddresses host memory then*datais set toMEMORYTYPE_HOST.If
ptrwas not allocated by, mapped by, or registered with aCUcontextwhich uses unified virtual addressing thenCUDA_ERROR_INVALID_VALUEis returned.If the current
CUcontextdoes not support unified virtual addressing thenCUDA_ERROR_INVALID_CONTEXTis returned.POINTER_ATTRIBUTE_DEVICE_POINTER: Returns in*datathe device pointer value through whichptrmay be accessed by kernels running in the currentCUcontext. The type ofdatamust beCUdeviceptr *.If there exists no device pointer value through which kernels running in the current
CUcontextmay accessptrthenCUDA_ERROR_INVALID_VALUEis returned.If there is no current
CUcontextthenCUDA_ERROR_INVALID_CONTEXTis returned.Except in the exceptional disjoint addressing cases discussed below, the value returned in
*datawill equal the input valueptr.POINTER_ATTRIBUTE_HOST_POINTER: Returns in*datathe host pointer value through whichptrmay be accessed by by the host program. The type ofdatamust bevoid **. If there exists no host pointer value through which the host program may directly accessptrthenCUDA_ERROR_INVALID_VALUEis returned.Except in the exceptional disjoint addressing cases discussed below, the value returned in
*datawill equal the input valueptr.POINTER_ATTRIBUTE_P2P_TOKENS: Returns in*datatwo tokens for use with the nv-p2p.h Linux kernel interface.datamust be a struct of typeCUDA_POINTER_ATTRIBUTE_P2P_TOKENS.ptrmust be a pointer to memory obtained fromMemAlloc. Note thatp2pTokenandvaSpaceTokenare only valid for the lifetime of the source allocation. A subsequent allocation at the same address may return completely different tokens. Querying this attribute has a side effect of setting the attributePOINTER_ATTRIBUTE_SYNC_MEMOPSfor the region of memory thatptrpoints to.POINTER_ATTRIBUTE_SYNC_MEMOPS:A boolean attribute which when set, ensures that synchronous memory operations initiated on the region of memory that
ptrpoints to will always synchronize. See further documentation in the section titled "API synchronization behavior" to learn more about cases when synchronous memory operations can exhibit asynchronous behavior.POINTER_ATTRIBUTE_BUFFER_ID: Returns in*dataa buffer ID which is guaranteed to be unique within the process.datamust point to an unsigned long long.ptrmust be a pointer to memory obtained from a CUDA memory allocation API. Every memory allocation from any of the CUDA memory allocation APIs will have a unique ID over a process lifetime. Subsequent allocations do not reuse IDs from previous freed allocations. IDs are only unique within a single process.POINTER_ATTRIBUTE_IS_MANAGED: Returns in*dataa boolean that indicates whether the pointer points to managed memory or not.If
ptris not a valid CUDA pointer thenCUDA_ERROR_INVALID_VALUEis returned.POINTER_ATTRIBUTE_DEVICE_ORDINAL: Returns in*dataan integer representing a device ordinal of a device against which the memory was allocated or registered.POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE: Returns in*dataa boolean that indicates if this pointer maps to an allocation that is suitable forcudaIpcGetMemHandle().POINTER_ATTRIBUTE_RANGE_START_ADDR: Returns in*datathe starting address for the allocation referenced by the device pointerptr. Note that this is not necessarily the address of the mapped region, but the address of the mappable address rangeptrreferences (e.g. fromMemAddressReserve).POINTER_ATTRIBUTE_RANGE_SIZE: Returns in*datathe size for the allocation referenced by the device pointerptr. Note that this is not necessarily the size of the mapped region, but the size of the mappable address rangeptrreferences (e.g. fromMemAddressReserve). To retrieve the size of the mapped region, seeMemGetAddressRange.POINTER_ATTRIBUTE_MAPPED: Returns in*dataa boolean that indicates if this pointer is in a valid address range that is mapped to a backing allocation.POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES: Returns a bitmask of the allowed handle types for an allocation that may be passed toMemExportToShareableHandle.POINTER_ATTRIBUTE_MEMPOOL_HANDLE: Returns in*datathe handle to the mempool that the allocation was obtained from.
Note that for most allocations in the unified virtual address space the host and device pointer for accessing the allocation will be the same. The exceptions to this are - user memory registered using
MemHostRegister- host memory allocated usingMemHostAllocwith theMEMHOSTALLOC_WRITECOMBINEDflag For these types of allocation there will exist separate, disjoint host and device addresses for accessing the allocation. In particular- The host address will correspond to an invalid unmapped device address (which will result in an exception if accessed from the device)
- The device address will correspond to an invalid unmapped host address (which will result in an exception if accessed from the host).
For these types of allocations, querying
POINTER_ATTRIBUTE_HOST_POINTERandPOINTER_ATTRIBUTE_DEVICE_POINTERmay be used to retrieve the host and device addresses from either address.- Parameters:
data- returned pointer attribute valueattribute- pointer attribute to queryptr- pointer
-
cuPointerGetAttribute
Returns information about a pointer.The supported attributes are:
POINTER_ATTRIBUTE_CONTEXT: Returns in*datatheCUcontextin whichptrwas allocated or registered. The type ofdatamust beCUcontext *.If
ptrwas not allocated by, mapped by, or registered with aCUcontextwhich uses unified virtual addressing thenCUDA_ERROR_INVALID_VALUEis returned.POINTER_ATTRIBUTE_MEMORY_TYPE:Returns in
*datathe physical memory type of the memory thatptraddresses as aCUmemorytypeenumerated value. The type ofdatamust be unsigned int.If
ptraddresses device memory then*datais set toMEMORYTYPE_DEVICE. The particularCUdeviceon which the memory resides is theCUdeviceof theCUcontextreturned by thePOINTER_ATTRIBUTE_CONTEXTattribute ofptr.If
ptraddresses host memory then*datais set toMEMORYTYPE_HOST.If
ptrwas not allocated by, mapped by, or registered with aCUcontextwhich uses unified virtual addressing thenCUDA_ERROR_INVALID_VALUEis returned.If the current
CUcontextdoes not support unified virtual addressing thenCUDA_ERROR_INVALID_CONTEXTis returned.POINTER_ATTRIBUTE_DEVICE_POINTER: Returns in*datathe device pointer value through whichptrmay be accessed by kernels running in the currentCUcontext. The type ofdatamust beCUdeviceptr *.If there exists no device pointer value through which kernels running in the current
CUcontextmay accessptrthenCUDA_ERROR_INVALID_VALUEis returned.If there is no current
CUcontextthenCUDA_ERROR_INVALID_CONTEXTis returned.Except in the exceptional disjoint addressing cases discussed below, the value returned in
*datawill equal the input valueptr.POINTER_ATTRIBUTE_HOST_POINTER: Returns in*datathe host pointer value through whichptrmay be accessed by by the host program. The type ofdatamust bevoid **. If there exists no host pointer value through which the host program may directly accessptrthenCUDA_ERROR_INVALID_VALUEis returned.Except in the exceptional disjoint addressing cases discussed below, the value returned in
*datawill equal the input valueptr.POINTER_ATTRIBUTE_P2P_TOKENS: Returns in*datatwo tokens for use with the nv-p2p.h Linux kernel interface.datamust be a struct of typeCUDA_POINTER_ATTRIBUTE_P2P_TOKENS.ptrmust be a pointer to memory obtained fromMemAlloc. Note thatp2pTokenandvaSpaceTokenare only valid for the lifetime of the source allocation. A subsequent allocation at the same address may return completely different tokens. Querying this attribute has a side effect of setting the attributePOINTER_ATTRIBUTE_SYNC_MEMOPSfor the region of memory thatptrpoints to.POINTER_ATTRIBUTE_SYNC_MEMOPS:A boolean attribute which when set, ensures that synchronous memory operations initiated on the region of memory that
ptrpoints to will always synchronize. See further documentation in the section titled "API synchronization behavior" to learn more about cases when synchronous memory operations can exhibit asynchronous behavior.POINTER_ATTRIBUTE_BUFFER_ID: Returns in*dataa buffer ID which is guaranteed to be unique within the process.datamust point to an unsigned long long.ptrmust be a pointer to memory obtained from a CUDA memory allocation API. Every memory allocation from any of the CUDA memory allocation APIs will have a unique ID over a process lifetime. Subsequent allocations do not reuse IDs from previous freed allocations. IDs are only unique within a single process.POINTER_ATTRIBUTE_IS_MANAGED: Returns in*dataa boolean that indicates whether the pointer points to managed memory or not.If
ptris not a valid CUDA pointer thenCUDA_ERROR_INVALID_VALUEis returned.POINTER_ATTRIBUTE_DEVICE_ORDINAL: Returns in*dataan integer representing a device ordinal of a device against which the memory was allocated or registered.POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE: Returns in*dataa boolean that indicates if this pointer maps to an allocation that is suitable forcudaIpcGetMemHandle().POINTER_ATTRIBUTE_RANGE_START_ADDR: Returns in*datathe starting address for the allocation referenced by the device pointerptr. Note that this is not necessarily the address of the mapped region, but the address of the mappable address rangeptrreferences (e.g. fromMemAddressReserve).POINTER_ATTRIBUTE_RANGE_SIZE: Returns in*datathe size for the allocation referenced by the device pointerptr. Note that this is not necessarily the size of the mapped region, but the size of the mappable address rangeptrreferences (e.g. fromMemAddressReserve). To retrieve the size of the mapped region, seeMemGetAddressRange.POINTER_ATTRIBUTE_MAPPED: Returns in*dataa boolean that indicates if this pointer is in a valid address range that is mapped to a backing allocation.POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES: Returns a bitmask of the allowed handle types for an allocation that may be passed toMemExportToShareableHandle.POINTER_ATTRIBUTE_MEMPOOL_HANDLE: Returns in*datathe handle to the mempool that the allocation was obtained from.
Note that for most allocations in the unified virtual address space the host and device pointer for accessing the allocation will be the same. The exceptions to this are - user memory registered using
MemHostRegister- host memory allocated usingMemHostAllocwith theMEMHOSTALLOC_WRITECOMBINEDflag For these types of allocation there will exist separate, disjoint host and device addresses for accessing the allocation. In particular- The host address will correspond to an invalid unmapped device address (which will result in an exception if accessed from the device)
- The device address will correspond to an invalid unmapped host address (which will result in an exception if accessed from the host).
For these types of allocations, querying
POINTER_ATTRIBUTE_HOST_POINTERandPOINTER_ATTRIBUTE_DEVICE_POINTERmay be used to retrieve the host and device addresses from either address.- Parameters:
data- returned pointer attribute valueattribute- pointer attribute to queryptr- pointer
-
cuPointerGetAttribute
Returns information about a pointer.The supported attributes are:
POINTER_ATTRIBUTE_CONTEXT: Returns in*datatheCUcontextin whichptrwas allocated or registered. The type ofdatamust beCUcontext *.If
ptrwas not allocated by, mapped by, or registered with aCUcontextwhich uses unified virtual addressing thenCUDA_ERROR_INVALID_VALUEis returned.POINTER_ATTRIBUTE_MEMORY_TYPE:Returns in
*datathe physical memory type of the memory thatptraddresses as aCUmemorytypeenumerated value. The type ofdatamust be unsigned int.If
ptraddresses device memory then*datais set toMEMORYTYPE_DEVICE. The particularCUdeviceon which the memory resides is theCUdeviceof theCUcontextreturned by thePOINTER_ATTRIBUTE_CONTEXTattribute ofptr.If
ptraddresses host memory then*datais set toMEMORYTYPE_HOST.If
ptrwas not allocated by, mapped by, or registered with aCUcontextwhich uses unified virtual addressing thenCUDA_ERROR_INVALID_VALUEis returned.If the current
CUcontextdoes not support unified virtual addressing thenCUDA_ERROR_INVALID_CONTEXTis returned.POINTER_ATTRIBUTE_DEVICE_POINTER: Returns in*datathe device pointer value through whichptrmay be accessed by kernels running in the currentCUcontext. The type ofdatamust beCUdeviceptr *.If there exists no device pointer value through which kernels running in the current
CUcontextmay accessptrthenCUDA_ERROR_INVALID_VALUEis returned.If there is no current
CUcontextthenCUDA_ERROR_INVALID_CONTEXTis returned.Except in the exceptional disjoint addressing cases discussed below, the value returned in
*datawill equal the input valueptr.POINTER_ATTRIBUTE_HOST_POINTER: Returns in*datathe host pointer value through whichptrmay be accessed by by the host program. The type ofdatamust bevoid **. If there exists no host pointer value through which the host program may directly accessptrthenCUDA_ERROR_INVALID_VALUEis returned.Except in the exceptional disjoint addressing cases discussed below, the value returned in
*datawill equal the input valueptr.POINTER_ATTRIBUTE_P2P_TOKENS: Returns in*datatwo tokens for use with the nv-p2p.h Linux kernel interface.datamust be a struct of typeCUDA_POINTER_ATTRIBUTE_P2P_TOKENS.ptrmust be a pointer to memory obtained fromMemAlloc. Note thatp2pTokenandvaSpaceTokenare only valid for the lifetime of the source allocation. A subsequent allocation at the same address may return completely different tokens. Querying this attribute has a side effect of setting the attributePOINTER_ATTRIBUTE_SYNC_MEMOPSfor the region of memory thatptrpoints to.POINTER_ATTRIBUTE_SYNC_MEMOPS:A boolean attribute which when set, ensures that synchronous memory operations initiated on the region of memory that
ptrpoints to will always synchronize. See further documentation in the section titled "API synchronization behavior" to learn more about cases when synchronous memory operations can exhibit asynchronous behavior.POINTER_ATTRIBUTE_BUFFER_ID: Returns in*dataa buffer ID which is guaranteed to be unique within the process.datamust point to an unsigned long long.ptrmust be a pointer to memory obtained from a CUDA memory allocation API. Every memory allocation from any of the CUDA memory allocation APIs will have a unique ID over a process lifetime. Subsequent allocations do not reuse IDs from previous freed allocations. IDs are only unique within a single process.POINTER_ATTRIBUTE_IS_MANAGED: Returns in*dataa boolean that indicates whether the pointer points to managed memory or not.If
ptris not a valid CUDA pointer thenCUDA_ERROR_INVALID_VALUEis returned.POINTER_ATTRIBUTE_DEVICE_ORDINAL: Returns in*dataan integer representing a device ordinal of a device against which the memory was allocated or registered.POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE: Returns in*dataa boolean that indicates if this pointer maps to an allocation that is suitable forcudaIpcGetMemHandle().POINTER_ATTRIBUTE_RANGE_START_ADDR: Returns in*datathe starting address for the allocation referenced by the device pointerptr. Note that this is not necessarily the address of the mapped region, but the address of the mappable address rangeptrreferences (e.g. fromMemAddressReserve).POINTER_ATTRIBUTE_RANGE_SIZE: Returns in*datathe size for the allocation referenced by the device pointerptr. Note that this is not necessarily the size of the mapped region, but the size of the mappable address rangeptrreferences (e.g. fromMemAddressReserve). To retrieve the size of the mapped region, seeMemGetAddressRange.POINTER_ATTRIBUTE_MAPPED: Returns in*dataa boolean that indicates if this pointer is in a valid address range that is mapped to a backing allocation.POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES: Returns a bitmask of the allowed handle types for an allocation that may be passed toMemExportToShareableHandle.POINTER_ATTRIBUTE_MEMPOOL_HANDLE: Returns in*datathe handle to the mempool that the allocation was obtained from.
Note that for most allocations in the unified virtual address space the host and device pointer for accessing the allocation will be the same. The exceptions to this are - user memory registered using
MemHostRegister- host memory allocated usingMemHostAllocwith theMEMHOSTALLOC_WRITECOMBINEDflag For these types of allocation there will exist separate, disjoint host and device addresses for accessing the allocation. In particular- The host address will correspond to an invalid unmapped device address (which will result in an exception if accessed from the device)
- The device address will correspond to an invalid unmapped host address (which will result in an exception if accessed from the host).
For these types of allocations, querying
POINTER_ATTRIBUTE_HOST_POINTERandPOINTER_ATTRIBUTE_DEVICE_POINTERmay be used to retrieve the host and device addresses from either address.- Parameters:
data- returned pointer attribute valueattribute- pointer attribute to queryptr- pointer
-
cuMemPrefetchAsync
public static int cuMemPrefetchAsync(long devPtr, long count, int dstDevice, long hStream) Prefetches memory to the specified destination device,Prefetches memory to the specified destination device.
devPtris the base device pointer of the memory to be prefetched anddstDeviceis the destination device.countspecifies the number of bytes to copy.hStreamis the stream in which the operation is enqueued. The memory range must refer to managed memory allocated viaMemAllocManagedor declared via __managed__ variables.Passing in
DEVICE_CPUfordstDevicewill prefetch the data to host memory. IfdstDeviceis a GPU, then the device attributeDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESSmust be non-zero. Additionally,hStreammust be associated with a device that has a non-zero value for the device attributeDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS.The start address and end address of the memory range will be rounded down and rounded up respectively to be aligned to CPU page size before the prefetch operation is enqueued in the stream.
If no physical memory has been allocated for this region, then this memory region will be populated and mapped on the destination device. If there's insufficient memory to prefetch the desired region, the Unified Memory driver may evict pages from other
MemAllocManagedallocations to host memory in order to make room. Device memory allocated usingMemAllocorArrayCreatewill not be evicted.By default, any mappings to the previous location of the migrated pages are removed and mappings for the new location are only setup on
dstDevice. The exact behavior however also depends on the settings applied to this memory range viaMemAdviseas described below:If
MEM_ADVISE_SET_READ_MOSTLYwas set on any subset of this memory range, then that subset will create a read-only copy of the pages ondstDevice.If
MEM_ADVISE_SET_PREFERRED_LOCATIONwas called on any subset of this memory range, then the pages will be migrated todstDeviceeven ifdstDeviceis not the preferred location of any pages in the memory range.If
MEM_ADVISE_SET_ACCESSED_BYwas called on any subset of this memory range, then mappings to those pages from all the appropriate processors are updated to refer to the new location if establishing such a mapping is possible. Otherwise, those mappings are cleared.Note that this API is not required for functionality and only serves to improve performance by allowing the application to migrate data to a suitable location before it is accessed. Memory accesses to this range are always coherent and are allowed even when the data is actively being migrated.
Note that this function is asynchronous with respect to the host and all work on other devices.
- Parameters:
devPtr- pointer to be prefetchedcount- size in bytesdstDevice- destination device to prefetch tohStream- stream to enqueue prefetch operation
-
cuMemAdvise
public static int cuMemAdvise(long devPtr, long count, int advice, int device) Advise about the usage of a given memory range.Advise the Unified Memory subsystem about the usage pattern for the memory range starting at
devPtrwith a size ofcountbytes. The start address and end address of the memory range will be rounded down and rounded up respectively to be aligned to CPU page size before the advice is applied. The memory range must refer to managed memory allocated viaMemAllocManagedor declared via __managed__ variables. The memory range could also refer to system-allocated pageable memory provided it represents a valid, host-accessible region of memory and all additional constraints imposed byadviceas outlined below are also satisfied. Specifying an invalid system-allocated pageable memory range results in an error being returned.The
adviceparameter can take the following values:MEM_ADVISE_SET_READ_MOSTLY: This implies that the data is mostly going to be read from and only occasionally written to. Any read accesses from any processor to this region will create a read-only copy of at least the accessed pages in that processor's memory. Additionally, ifMemPrefetchAsyncis called on this region, it will create a read-only copy of the data on the destination processor. If any processor writes to this region, all copies of the corresponding page will be invalidated except for the one where the write occurred. Thedeviceargument is ignored for this advice. Note that for a page to be read-duplicated, the accessing processor must either be the CPU or a GPU that has a non-zero value for the device attributeDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS. Also, if a context is created on a device that does not have the device attributeDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESSset, then read-duplication will not occur until all such contexts are destroyed. If the memory region refers to valid system-allocated pageable memory, then the accessing device must have a non-zero value for the device attributeDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESSfor a read-only copy to be created on that device. Note however that if the accessing device also has a non-zero value for the device attributeDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES, then setting this advice will not create a read-only copy when that device accesses this memory region.MEM_ADVISE_UNSET_READ_MOSTLY: Undoes the effect ofMEM_ADVISE_SET_READ_MOSTLYand also prevents the Unified Memory driver from attempting heuristic read-duplication on the memory range. Any read-duplicated copies of the data will be collapsed into a single copy. The location for the collapsed copy will be the preferred location if the page has a preferred location and one of the read-duplicated copies was resident at that location. Otherwise, the location chosen is arbitrary.MEM_ADVISE_SET_PREFERRED_LOCATION: This advice sets the preferred location for the data to be the memory belonging todevice. Passing in CU_DEVICE_CPU fordevicesets the preferred location as host memory. Ifdeviceis a GPU, then it must have a non-zero value for the device attributeDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS. Setting the preferred location does not cause data to migrate to that location immediately. Instead, it guides the migration policy when a fault occurs on that memory region. If the data is already in its preferred location and the faulting processor can establish a mapping without requiring the data to be migrated, then data migration will be avoided. On the other hand, if the data is not in its preferred location or if a direct mapping cannot be established, then it will be migrated to the processor accessing it. It is important to note that setting the preferred location does not prevent data prefetching done usingMemPrefetchAsync. Having a preferred location can override the page thrash detection and resolution logic in the Unified Memory driver. Normally, if a page is detected to be constantly thrashing between for example host and device memory, the page may eventually be pinned to host memory by the Unified Memory driver. But if the preferred location is set as device memory, then the page will continue to thrash indefinitely. IfMEM_ADVISE_SET_READ_MOSTLYis also set on this memory region or any subset of it, then the policies associated with that advice will override the policies of this advice, unless read accesses fromdevicewill not result in a read-only copy being created on that device as outlined in description for the adviceMEM_ADVISE_SET_READ_MOSTLY. If the memory region refers to valid system-allocated pageable memory, thendevicemust have a non-zero value for the device attributeDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS. Additionally, ifdevicehas a non-zero value for the device attributeDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES, then this call has no effect. Note however that this behavior may change in the future.MEM_ADVISE_UNSET_PREFERRED_LOCATION: Undoes the effect ofMEM_ADVISE_SET_PREFERRED_LOCATIONand changes the preferred location to none.MEM_ADVISE_SET_ACCESSED_BY: This advice implies that the data will be accessed bydevice. Passing inDEVICE_CPUfordevicewill set the advice for the CPU. Ifdeviceis a GPU, then the device attributeDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESSmust be non-zero. This advice does not cause data migration and has no impact on the location of the data per se. Instead, it causes the data to always be mapped in the specified processor's page tables, as long as the location of the data permits a mapping to be established. If the data gets migrated for any reason, the mappings are updated accordingly. This advice is recommended in scenarios where data locality is not important, but avoiding faults is. Consider for example a system containing multiple GPUs with peer-to-peer access enabled, where the data located on one GPU is occasionally accessed by peer GPUs. In such scenarios, migrating data over to the other GPUs is not as important because the accesses are infrequent and the overhead of migration may be too high. But preventing faults can still help improve performance, and so having a mapping set up in advance is useful. Note that on CPU access of this data, the data may be migrated to host memory because the CPU typically cannot access device memory directly. Any GPU that had theMEM_ADVISE_SET_ACCESSED_BYflag set for this data will now have its mapping updated to point to the page in host memory. IfMEM_ADVISE_SET_READ_MOSTLYis also set on this memory region or any subset of it, then the policies associated with that advice will override the policies of this advice. Additionally, if the preferred location of this memory region or any subset of it is alsodevice, then the policies associated withMEM_ADVISE_SET_PREFERRED_LOCATIONwill override the policies of this advice. If the memory region refers to valid system-allocated pageable memory, thendevicemust have a non-zero value for the device attributeDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS. Additionally, ifdevicehas a non-zero value for the device attributeDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES, then this call has no effect.MEM_ADVISE_UNSET_ACCESSED_BY: Undoes the effect ofMEM_ADVISE_SET_ACCESSED_BY. Any mappings to the data fromdevicemay be removed at any time causing accesses to result in non-fatal page faults. If the memory region refers to valid system-allocated pageable memory, thendevicemust have a non-zero value for the device attributeDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS. Additionally, ifdevicehas a non-zero value for the device attributeDEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES, then this call has no effect.
- Parameters:
devPtr- pointer to memory to set the advice forcount- size in bytes of the memory rangeadvice- advice to be applied for the specified memory rangedevice- device to apply the advice for
-
ncuMemRangeGetAttribute
public static int ncuMemRangeGetAttribute(long data, long dataSize, int attribute, long devPtr, long count) Unsafe version of:MemRangeGetAttribute- Parameters:
dataSize- the size ofdata
-
cuMemRangeGetAttribute
Query an attribute of a given memory range.Query an attribute about the memory range starting at
devPtrwith a size ofcountbytes. The memory range must refer to managed memory allocated viaMemAllocManagedor declared via __managed__ variables.The
attributeparameter can take the following values:MEM_RANGE_ATTRIBUTE_READ_MOSTLY: If this attribute is specified,datawill be interpreted as a 32-bit integer, anddataSizemust be 4. The result returned will be 1 if all pages in the given memory range have read-duplication enabled, or 0 otherwise.MEM_RANGE_ATTRIBUTE_PREFERRED_LOCATION: If this attribute is specified,datawill be interpreted as a 32-bit integer, anddataSizemust be 4. The result returned will be a GPU device id if all pages in the memory range have that GPU as their preferred location, or it will be CU_DEVICE_CPU if all pages in the memory range have the CPU as their preferred location, or it will be CU_DEVICE_INVALID if either all the pages don't have the same preferred location or some of the pages don't have a preferred location at all. Note that the actual location of the pages in the memory range at the time of the query may be different from the preferred location.MEM_RANGE_ATTRIBUTE_ACCESSED_BY: If this attribute is specified,datawill be interpreted as an array of 32-bit integers, anddataSizemust be a non-zero multiple of 4. The result returned will be a list of device ids that hadMEM_ADVISE_SET_ACCESSED_BYset for that entire memory range. If any device does not have that advice set for the entire memory range, that device will not be included. Ifdatais larger than the number of devices that have that advice set for that memory range, CU_DEVICE_INVALID will be returned in all the extra space provided. For ex., ifdataSizeis 12 (i.e.datahas 3 elements) and only device 0 has the advice set, then the result returned will be { 0, CU_DEVICE_INVALID, CU_DEVICE_INVALID }. Ifdatais smaller than the number of devices that have that advice set, then only as many devices will be returned as can fit in the array. There is no guarantee on which specific devices will be returned, however.MEM_RANGE_ATTRIBUTE_LAST_PREFETCH_LOCATION: If this attribute is specified,datawill be interpreted as a 32-bit integer, anddataSizemust be 4. The result returned will be the last location to which all pages in the memory range were prefetched explicitly viaMemPrefetchAsync. This will either be a GPU id or CU_DEVICE_CPU depending on whether the last location for prefetch was a GPU or the CPU respectively. If any page in the memory range was never explicitly prefetched or if all pages were not prefetched to the same location, CU_DEVICE_INVALID will be returned. Note that this simply returns the last location that the applicaton requested to prefetch the memory range to. It gives no indication as to whether the prefetch operation to that location has completed or even begun.
- Parameters:
data- a pointers to a memory location where the result of each attribute query will be written toattribute- the attribute to querydevPtr- start of the range to querycount- size of the range to query
-
ncuMemRangeGetAttributes
public static int ncuMemRangeGetAttributes(long data, long dataSizes, long attributes, long numAttributes, long devPtr, long count) Unsafe version of:MemRangeGetAttributes- Parameters:
numAttributes- number of attributes to query
-
cuMemRangeGetAttributes
public static int cuMemRangeGetAttributes(PointerBuffer data, PointerBuffer dataSizes, IntBuffer attributes, long devPtr, long count) Query attributes of a given memory range.Query attributes of the memory range starting at
devPtrwith a size ofcountbytes. The memory range must refer to managed memory allocated viaMemAllocManagedor declared via __managed__ variables. Theattributesarray will be interpreted to havenumAttributesentries. ThedataSizesarray will also be interpreted to havenumAttributesentries. The results of the query will be stored indata.The list of supported attributes are given below. Please refer to
MemRangeGetAttributefor attribute descriptions and restrictions.- Parameters:
data- a two-dimensional array containing pointers to memory locations where the result of each attribute query will be written todataSizes- array containing the sizes of each resultattributes- an array of attributes to query (numAttributes and the number of attributes in this array should match). One of:MEM_RANGE_ATTRIBUTE_READ_MOSTLYMEM_RANGE_ATTRIBUTE_PREFERRED_LOCATIONMEM_RANGE_ATTRIBUTE_ACCESSED_BYMEM_RANGE_ATTRIBUTE_LAST_PREFETCH_LOCATIONdevPtr- start of the range to querycount- size of the range to query
-
ncuPointerSetAttribute
public static int ncuPointerSetAttribute(long value, int attribute, long ptr) Unsafe version of:PointerSetAttribute -
cuPointerSetAttribute
Set attributes on a previously allocated memory region.The supported attributes are:
POINTER_ATTRIBUTE_SYNC_MEMOPS: A boolean attribute that can either be set (1) or unset (0).When set, the region of memory that
ptrpoints to is guaranteed to always synchronize memory operations that are synchronous. If there are some previously initiated synchronous memory operations that are pending when this attribute is set, the function does not return until those memory operations are complete. See further documentation in the section titled "API synchronization behavior" to learn more about cases when synchronous memory operations can exhibit asynchronous behavior.valuewill be considered as a pointer to an unsigned integer to which this attribute is to be set.
- Parameters:
value- pointer to memory containing the value to be setattribute- pointer attribute to setptr- pointer to a memory region allocated using CUDA memory allocation APIs
-
ncuPointerGetAttributes
public static int ncuPointerGetAttributes(int numAttributes, long attributes, long data, long ptr) Unsafe version of:PointerGetAttributes- Parameters:
numAttributes- number of attributes to query
-
cuPointerGetAttributes
Returns information about a pointer.Unlike
PointerGetAttribute, this function will not return an error when theptrencountered is not a valid CUDA pointer. Instead, the attributes are assigned defaultNULLvalues andCUDA_SUCCESSis returned.If
ptrwas not allocated by, mapped by, or registered with aCUcontextwhich uses UVA (Unified Virtual Addressing),CUDA_ERROR_INVALID_CONTEXTis returned.- Parameters:
attributes- an array of attributes to query (numAttributes and the number of attributes in this array should match). One of:data- a two-dimensional array containing pointers to memory locations where the result of each attribute query will be written toptr- pointer to query
-
ncuStreamCreate
public static int ncuStreamCreate(long phStream, int Flags) Unsafe version of:StreamCreate -
cuStreamCreate
Create a stream.Creates a stream and returns a handle in
phStream. TheFlagsargument determines behaviors of the stream.Valid values for
Flagsare:STREAM_DEFAULT: Default stream creation flag.STREAM_NON_BLOCKING: Specifies that work running in the created stream may run concurrently with work in stream 0 (the NULL stream), and that the created stream should perform no implicit synchronization with stream 0.
- Parameters:
phStream- returned newly created streamFlags- parameters for stream creation
-
ncuStreamCreateWithPriority
public static int ncuStreamCreateWithPriority(long phStream, int flags, int priority) Unsafe version of:StreamCreateWithPriority -
cuStreamCreateWithPriority
Create a stream with the given priority.Creates a stream with the specified priority and returns a handle in
phStream. This API alters the scheduler priority of work in the stream. Work in a higher priority stream may preempt work already executing in a low priority stream.priorityfollows a convention where lower numbers represent higher priorities.0represents default priority. The range of meaningful numerical priorities can be queried usingCtxGetStreamPriorityRange. If the specified priority is outside the numerical range returned byCtxGetStreamPriorityRange, it will automatically be clamped to the lowest or the highest number in the range.Note
Stream priorities are supported only on GPUs with compute capability 3.5 or higher.
Note
In the current implementation, only compute kernels launched in priority streams are affected by the stream's priority. Stream priorities have no effect on host-to-device and device-to-host memory operations.
- Parameters:
phStream- returned newly created streamflags- flags for stream creation. SeeStreamCreatefor a list of valid flagspriority- stream priority. Lower numbers represent higher priorities. SeeCtxGetStreamPriorityRangefor more information about meaningful stream priorities that can be passed.
-
ncuStreamGetPriority
public static int ncuStreamGetPriority(long hStream, long priority) Unsafe version of:StreamGetPriority -
cuStreamGetPriority
Query the priority of a given stream.Query the priority of a stream created using
StreamCreateorStreamCreateWithPriorityand return the priority inpriority. Note that if the stream was created with a priority outside the numerical range returned byCtxGetStreamPriorityRange, this function returns the clamped priority. SeeStreamCreateWithPriorityfor details about priority clamping.- Parameters:
hStream- handle to the stream to be queriedpriority- pointer to a signed integer in which the stream's priority is returned
-
ncuStreamGetFlags
public static int ncuStreamGetFlags(long hStream, long flags) Unsafe version of:StreamGetFlags -
cuStreamGetFlags
Query the flags of a given stream.Query the flags of a stream created using
StreamCreateorStreamCreateWithPriorityand return the flags inflags.- Parameters:
hStream- handle to the stream to be queriedflags- pointer to an unsigned integer in which the stream's flags are returned The value returned inflagsis a logical 'OR' of all flags that were used while creating this stream. SeeStreamCreatefor the list of valid flags.
-
ncuStreamGetCtx
public static int ncuStreamGetCtx(long hStream, long pctx) Unsafe version of:StreamGetCtx -
cuStreamGetCtx
Query the context associated with a stream.Returns the CUDA context that the stream is associated with.
The stream handle
hStreamcan refer to any of the following:- a stream created via any of the CUDA driver APIs such as
StreamCreateandStreamCreateWithPriority, or their runtime API equivalents such ascudaStreamCreate(),cudaStreamCreateWithFlags()andcudaStreamCreateWithPriority(). The returned context is the context that was active in the calling thread when the stream was created. Passing an invalid handle will result in undefined behavior. - any of the special streams such as the
NULLstream,STREAM_LEGACYandSTREAM_PER_THREAD. The runtime API equivalents of these are also accepted, which areNULL,cudaStreamLegacy()andcudaStreamPerThread()respectively. Specifying any of the special handles will return the context current to the calling thread. If no context is current to the calling thread,CUDA_ERROR_INVALID_CONTEXTis returned.
- Parameters:
hStream- handle to the stream to be queriedpctx- returned context associated with the stream
- a stream created via any of the CUDA driver APIs such as
-
cuStreamWaitEvent
public static int cuStreamWaitEvent(long hStream, long hEvent, int Flags) Make a compute stream wait on an event.Makes all future work submitted to
hStreamwait for all work captured inhEvent. SeeEventRecordfor details on what is captured by an event. The synchronization will be performed efficiently on the device when applicable.hEventmay be from a different context or device thanhStream.- Parameters:
hStream- stream to waithEvent- event to wait on (may not beNULL). One of:EVENT_WAIT_DEFAULTEVENT_WAIT_EXTERNALFlags- seeCUevent_capture_flags
-
ncuStreamAddCallback
public static int ncuStreamAddCallback(long hStream, long callback, long userData, int flags) Unsafe version of:StreamAddCallback -
cuStreamAddCallback
public static int cuStreamAddCallback(long hStream, CUstreamCallbackI callback, long userData, int flags) Add a callback to a compute stream.Note
This function is slated for eventual deprecation and removal. If you do not require the callback to execute in case of a device error, consider using
LaunchHostFunc. Additionally, this function is not supported withStreamBeginCaptureandStreamEndCapture, unlikeLaunchHostFunc.Adds a callback to be called on the host after all currently enqueued items in the stream have completed. For each
cuStreamAddCallbackcall, the callback will be executed exactly once. The callback will block later work in the stream until it is finished.The callback may be passed
CUDA_SUCCESSor an error code. In the event of a device error, all subsequently executed callbacks will receive an appropriateCUresult.Callbacks must not make any CUDA API calls. Attempting to use a CUDA API will result in
CUDA_ERROR_NOT_PERMITTED. Callbacks must not perform any synchronization that may depend on outstanding device work or other callbacks that are not mandated to run earlier. Callbacks without a mandated order (in independent streams) execute in undefined order and may be serialized.For the purposes of Unified Memory, callback execution makes a number of guarantees:
- The callback stream is considered idle for the duration of the callback. Thus, for example, a callback may always use memory attached to the callback stream.
- The start of execution of a callback has the same effect as synchronizing an event recorded in the same stream immediately prior to the callback. It thus synchronizes streams which have been "joined" prior to the callback.
- Adding device work to any stream does not have the effect of making the stream active until all preceding host functions and stream callbacks have executed. Thus, for example, a callback might use global attached memory even if work has been added to another stream, if the work has been ordered behind the callback with an event.
- Completion of a callback does not cause a stream to become active except as described above. The callback stream will remain idle if no device work follows the callback, and will remain idle across consecutive callbacks without device work in between. Thus, for example, stream synchronization can be done by signaling from a callback at the end of the stream.
- Parameters:
hStream- stream to add callback tocallback- the function to call once preceding stream operations are completeuserData- user specified data to be passed to the callback functionflags- reserved for future use, must be 0
-
cuStreamBeginCapture
public static int cuStreamBeginCapture(long hStream) Begins graph capture on a stream.Begin graph capture on
hStream. When a stream is in capture mode, all operations pushed into the stream will not be executed, but will instead be captured into a graph, which will be returned viaStreamEndCapture. Capture may not be initiated ifstreamisSTREAM_LEGACY. Capture must be ended on the same stream in which it was initiated, and it may only be initiated if the stream is not already in capture mode. The capture mode may be queried viaStreamIsCapturing. A unique id representing the capture sequence may be queried viaStreamGetCaptureInfo.Note
Kernels captured using this API must not use texture and surface references. Reading or writing through any texture or surface reference is undefined behavior. This restriction does not apply to texture and surface objects.
- Parameters:
hStream- stream in which to initiate capture
-
cuStreamBeginCapture_v2
public static int cuStreamBeginCapture_v2(long hStream, int mode) Begins graph capture on a stream.Begin graph capture on
hStream. When a stream is in capture mode, all operations pushed into the stream will not be executed, but will instead be captured into a graph, which will be returned viaStreamEndCapture. Capture may not be initiated ifstreamisSTREAM_LEGACY. Capture must be ended on the same stream in which it was initiated, and it may only be initiated if the stream is not already in capture mode. The capture mode may be queried viaStreamIsCapturing. A unique id representing the capture sequence may be queried viaStreamGetCaptureInfo.If
modeis notSTREAM_CAPTURE_MODE_RELAXED,StreamEndCapturemust be called on this stream from the same thread.Note
Kernels captured using this API must not use texture and surface references. Reading or writing through any texture or surface reference is undefined behavior. This restriction does not apply to texture and surface objects.
- Parameters:
hStream- stream in which to initiate capturemode- controls the interaction of this capture sequence with other API calls that are potentially unsafe. For more details seeThreadExchangeStreamCaptureMode.
-
ncuThreadExchangeStreamCaptureMode
public static int ncuThreadExchangeStreamCaptureMode(long mode) Unsafe version of:ThreadExchangeStreamCaptureMode -
cuThreadExchangeStreamCaptureMode
Swaps the stream capture interaction mode for a thread.Sets the calling thread's stream capture interaction mode to the value contained in
*mode, and overwrites*modewith the previous mode for the thread. To facilitate deterministic behavior across function or module boundaries, callers are encouraged to use this API in a push-pop fashion:CUstreamCaptureMode mode = desiredMode cuThreadExchangeStreamCaptureMode(&mode); ... cuThreadExchangeStreamCaptureMode(&mode); // restore previous modeDuring stream capture (see
StreamBeginCapture), some actions, such as a call tocudaMalloc, may be unsafe. In the case ofcudaMalloc, the operation is not enqueued asynchronously to a stream, and is not observed by stream capture. Therefore, if the sequence of operations captured viaStreamBeginCapturedepended on the allocation being replayed whenever the graph is launched, the captured graph would be invalid.Therefore, stream capture places restrictions on API calls that can be made within or concurrently to a
StreamBeginCapture-StreamEndCapturesequence. This behavior can be controlled via this API and flags tocuStreamBeginCapture.A thread's mode is one of the following:
STREAM_CAPTURE_MODE_GLOBAL: This is the default mode.If the local thread has an ongoing capture sequence that was not initiated with
STREAM_CAPTURE_MODE_RELAXEDatStreamBeginCapture, or if any other thread has a concurrent capture sequence initiated withSTREAM_CAPTURE_MODE_GLOBAL, this thread is prohibited from potentially unsafe API calls.STREAM_CAPTURE_MODE_THREAD_LOCAL: If the local thread has an ongoing capture sequence not initiated withCU_STREAM_CAPTURE_MODE_RELAXED, it is prohibited from potentially unsafe API calls. Concurrent capture sequences in other threads are ignored.STREAM_CAPTURE_MODE_RELAXED: The local thread is not prohibited from potentially unsafe API calls. Note that the thread is still prohibited from API calls which necessarily conflict with stream capture, for example, attemptingEventQueryon an event that was last recorded inside a capture sequence.
- Parameters:
mode- pointer to mode value to swap with the current mode
-
ncuStreamEndCapture
public static int ncuStreamEndCapture(long hStream, long phGraph) Unsafe version of:StreamEndCapture -
cuStreamEndCapture
Ends capture on a stream, returning the captured graph.End capture on
hStream, returning the captured graph viaphGraph. Capture must have been initiated onhStreamvia a call toStreamBeginCapture. If capture was invalidated, due to a violation of the rules of stream capture, then a NULL graph will be returned.If the
modeargument toStreamBeginCapturewas notSTREAM_CAPTURE_MODE_RELAXED, this call must be from the same thread asStreamBeginCapture.- Parameters:
hStream- stream to queryphGraph- the captured graph
-
ncuStreamIsCapturing
public static int ncuStreamIsCapturing(long hStream, long captureStatus) Unsafe version of:StreamIsCapturing -
cuStreamIsCapturing
Returns a stream's capture status.Return the capture status of
hStreamviacaptureStatus. After a successful call,*captureStatuswill contain one of the following:STREAM_CAPTURE_STATUS_NONE: The stream is not capturing.STREAM_CAPTURE_STATUS_ACTIVE: The stream is capturing.STREAM_CAPTURE_STATUS_INVALIDATED: The stream was capturing but an error has invalidated the capture sequence. The capture sequence must be terminated withStreamEndCaptureon the stream where it was initiated in order to continue usinghStream.
Note that, if this is called on
STREAM_LEGACY(the "null stream") while a blocking stream in the same context is capturing, it will returnCUDA_ERROR_STREAM_CAPTURE_IMPLICITand*captureStatusis unspecified after the call. The blocking stream capture is not invalidated.When a blocking stream is capturing, the legacy stream is in an unusable state until the blocking stream capture is terminated. The legacy stream is not supported for stream capture, but attempted use would have an implicit dependency on the capturing stream(s).
- Parameters:
hStream- stream to querycaptureStatus- returns the stream's capture status
-
ncuStreamGetCaptureInfo
public static int ncuStreamGetCaptureInfo(long hStream, long captureStatus, long id) Unsafe version of:StreamGetCaptureInfo -
cuStreamGetCaptureInfo
Query capture status of a stream.Query the capture status of a stream and and get an id for the capture sequence, which is unique over the lifetime of the process.
If called on
STREAM_LEGACY(the "null stream") while a stream not created withSTREAM_NON_BLOCKINGis capturing, returnsCUDA_ERROR_STREAM_CAPTURE_IMPLICIT.A valid id is returned only if both of the following are true:
- the call returns
SUCCESS captureStatusis set toSTREAM_CAPTURE_STATUS_ACTIVE
- the call returns
-
ncuStreamGetCaptureInfo_v2
public static int ncuStreamGetCaptureInfo_v2(long hStream, long captureStatus_out, long id_out, long graph_out, long dependencies_out, long numDependencies_out) Unsafe version of:StreamGetCaptureInfo_v2 -
cuStreamGetCaptureInfo_v2
public static int cuStreamGetCaptureInfo_v2(long hStream, IntBuffer captureStatus_out, @Nullable LongBuffer id_out, @Nullable PointerBuffer graph_out, @Nullable PointerBuffer dependencies_out, @Nullable PointerBuffer numDependencies_out) Query a stream's capture state (11.3+).Query stream state related to stream capture.
If called on
STREAM_LEGACY(the "null stream") while a stream not created withSTREAM_NON_BLOCKINGis capturing, returnsCUDA_ERROR_STREAM_CAPTURE_IMPLICIT.Valid data (other than capture status) is returned only if both of the following are true:
- the call returns CUDA_SUCCESS
- the returned capture status is
STREAM_CAPTURE_STATUS_ACTIVE
This version of
cuStreamGetCaptureInfois introduced in CUDA 11.3 and will supplant the previous version in 12.0. Developers requiring compatibility across minor versions to CUDA 11.0 (driver version 445) should useStreamGetCaptureInfoor include a fallback path.- Parameters:
hStream- the stream to querycaptureStatus_out- location to return the capture status of the stream; requiredid_out- optional location to return an id for the capture sequence, which is unique over the lifetime of the processgraph_out- optional location to return the graph being captured into.All operations other than destroy and node removal are permitted on the graph while the capture sequence is in progress. This API does not transfer ownership of the graph, which is transferred or destroyed at
StreamEndCapture. Note that the graph handle may be invalidated before end of capture for certain errors. Nodes that are or become unreachable from the original stream atStreamEndCapturedue to direct actions on the graph do not triggerCUDA_ERROR_STREAM_CAPTURE_UNJOINED.dependencies_out- optional location to store a pointer to an array of nodes.The next node to be captured in the stream will depend on this set of nodes, absent operations such as event wait which modify this set. The array pointer is valid until the next API call which operates on the stream or until end of capture. The node handles may be copied out and are valid until they or the graph is destroyed. The driver-owned array may also be passed directly to APIs that operate on the graph (not the stream) without copying.
numDependencies_out- optional location to store the size of the array returned independencies_out
-
ncuStreamUpdateCaptureDependencies
public static int ncuStreamUpdateCaptureDependencies(long hStream, long dependencies, long numDependencies, int flags) Unsafe version of:StreamUpdateCaptureDependencies -
cuStreamUpdateCaptureDependencies
public static int cuStreamUpdateCaptureDependencies(long hStream, PointerBuffer dependencies, int flags) Update the set of dependencies in a capturing stream (11.3+).Modifies the dependency set of a capturing stream. The dependency set is the set of nodes that the next captured node in the stream will depend on.
Valid flags are
STREAM_ADD_CAPTURE_DEPENDENCIESandSTREAM_SET_CAPTURE_DEPENDENCIES. These control whether the set passed to the API is added to the existing set or replaces it. A flags value of 0 defaults toSTREAM_ADD_CAPTURE_DEPENDENCIES.Nodes that are removed from the dependency set via this API do not result in
CUDA_ERROR_STREAM_CAPTURE_UNJOINEDif they are unreachable from the stream atStreamEndCapture.Returns
CUDA_ERROR_ILLEGAL_STATEif the stream is not capturing.This API is new in CUDA 11.3. Developers requiring compatibility across minor versions to CUDA 11.0 should not use this API or provide a fallback.
-
cuStreamAttachMemAsync
public static int cuStreamAttachMemAsync(long hStream, long dptr, long length, int flags) Attach memory to a stream asynchronously.Enqueues an operation in
hStreamto specify stream association oflengthbytes of memory starting fromdptr. This function is a stream-ordered operation, meaning that it is dependent on, and will only take effect when, previous work in stream has completed. Any previous association is automatically replaced.dptrmust point to one of the following types of memories:- managed memory declared using the __managed__ keyword or allocated with
MemAllocManaged. - a valid host-accessible region of system-allocated pageable memory. This type of memory may only be specified if the device associated with the
stream reports a non-zero value for the device attribute
DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS.
For managed allocations,
lengthmust be either zero or the entire allocation's size. Both indicate that the entire allocation's stream association is being changed. Currently, it is not possible to change stream association for a portion of a managed allocation.For pageable host allocations,
lengthmust be non-zero.The stream association is specified using
flagswhich must be one ofCUmemAttach_flags. If theMEM_ATTACH_GLOBALflag is specified, the memory can be accessed by any stream on any device. If theMEM_ATTACH_HOSTflag is specified, the program makes a guarantee that it won't access the memory on the device from any stream on a device that has a zero value for the device attributeDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS. If theMEM_ATTACH_SINGLEflag is specified andhStreamis associated with a device that has a zero value for the device attributeDEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS, the program makes a guarantee that it will only access the memory on the device fromhStream. It is illegal to attach singly to the NULL stream, because the NULL stream is a virtual global stream and not a specific stream. An error will be returned in this case.When memory is associated with a single stream, the Unified Memory system will allow CPU access to this memory region so long as all operations in
hStreamhave completed, regardless of whether other streams are active. In effect, this constrains exclusive ownership of the managed memory region by an active GPU to per-stream activity instead of whole-GPU activity.Accessing memory on the device from streams that are not associated with it will produce undefined results. No error checking is performed by the Unified Memory system to ensure that kernels launched into other streams do not access this region.
It is a program's responsibility to order calls to
StreamAttachMemAsyncvia events, synchronization or other means to ensure legal access to memory at all times. Data visibility and coherency will be changed appropriately for all kernels which follow a stream-association change.If
hStreamis destroyed while data is associated with it, the association is removed and the association reverts to the default visibility of the allocation as specified atMemAllocManaged. For __managed__ variables, the default association is alwaysMEM_ATTACH_GLOBAL. Note that destroying a stream is an asynchronous operation, and as a result, the change to default association won't happen until all work in the stream has completed.- Parameters:
hStream- stream in which to enqueue the attach operationdptr- pointer to memory (must be a pointer to managed memory or to a valid host-accessible region of system-allocated pageable memory)length- length of memoryflags- must be one ofCUmemAttach_flags
- managed memory declared using the __managed__ keyword or allocated with
-
cuStreamQuery
public static int cuStreamQuery(long hStream) Determine status of a compute stream.Returns
CUDA_SUCCESSif all operations in the stream specified byhStreamhave completed, orCUDA_ERROR_NOT_READYif not.For the purposes of Unified Memory, a return value of
CUDA_SUCCESSis equivalent to having calledStreamSynchronize.- Parameters:
hStream- stream to query status of
-
cuStreamSynchronize
public static int cuStreamSynchronize(long hStream) Wait until a stream's tasks are completed.Waits until the device has completed all operations in the stream specified by
hStream. If the context was created with theCTX_SCHED_BLOCKING_SYNCflag, the CPU thread will block until the stream is finished with all of its tasks.- Parameters:
hStream- stream to wait for
-
cuStreamDestroy
public static int cuStreamDestroy(long hStream) Destroys a stream.Destroys the stream specified by
hStream.In case the device is still doing work in the stream
hStreamwhenStreamDestroyis called, the function will return immediately and the resources associated withhStreamwill be released automatically once the device has completed all work inhStream.- Parameters:
hStream- stream to destroy
-
cuStreamCopyAttributes
public static int cuStreamCopyAttributes(long dst, long src) Copies attributes from source stream to destination stream.Copies attributes from source stream
srcto destination streamdst. Both streams must have the same context.- Parameters:
dst- destination streamsrc- source stream For list of attributes seeCUstreamAttrID
-
ncuStreamGetAttribute
public static int ncuStreamGetAttribute(long hStream, int attr, long value_out) Unsafe version of:StreamGetAttribute -
cuStreamGetAttribute
Queries stream attribute.Queries attribute
attrfromhStreamand stores it in corresponding member ofvalue_out. -
ncuStreamSetAttribute
public static int ncuStreamSetAttribute(long hStream, int attr, long value) Unsafe version of:StreamSetAttribute -
cuStreamSetAttribute
Sets stream attribute.Sets attribute
attronhStreamfrom corresponding attribute ofvalue. The updated attribute will be applied to subsequent work submitted to the stream. It will not affect previously submitted work. -
ncuEventCreate
public static int ncuEventCreate(long phEvent, int Flags) Unsafe version of:EventCreate -
cuEventCreate
Creates an event.Creates an event
*phEventfor the current context with the flags specified viaFlags. Valid flags include:EVENT_DEFAULT: Default event creation flag.EVENT_BLOCKING_SYNC: Specifies that the created event should use blocking synchronization. A CPU thread that usesEventSynchronizeto wait on an event created with this flag will block until the event has actually been recorded.EVENT_DISABLE_TIMING: Specifies that the created event does not need to record timing data. Events created with this flag specified and theEVENT_BLOCKING_SYNCflag not specified will provide the best performance when used withStreamWaitEventandEventQuery.EVENT_INTERPROCESS: Specifies that the created event may be used as an interprocess event byIpcGetEventHandle.EVENT_INTERPROCESSmust be specified along withEVENT_DISABLE_TIMING.
- Parameters:
phEvent- returns newly created eventFlags- event creation flags
-
cuEventRecord
public static int cuEventRecord(long hEvent, long hStream) Records an event.Captures in
hEventthe contents ofhStreamat the time of this call.hEventandhStreammust be from the same context. Calls such asEventQueryorStreamWaitEventwill then examine or wait for completion of the work that was captured. Uses ofhStreamafter this call do not modifyhEvent. See note on default stream behavior for what is captured in the default case.EventRecordcan be called multiple times on the same event and will overwrite the previously captured state. Other APIs such asStreamWaitEventuse the most recently captured state at the time of the API call, and are not affected by later calls toEventRecord. Before the first call toEventRecord, an event represents an empty set of work, so for exampleEventQuerywould returnCUDA_SUCCESS.- Parameters:
hEvent- event to recordhStream- stream to record event for
-
cuEventRecordWithFlags
public static int cuEventRecordWithFlags(long hEvent, long hStream, int flags) Records an event.Captures in
hEventthe contents ofhStreamat the time of this call.hEventandhStreammust be from the same context. Calls such asEventQueryorStreamWaitEventwill then examine or wait for completion of the work that was captured. Uses ofhStreamafter this call do not modifyhEvent. See note on default stream behavior for what is captured in the default case.EventRecordWithFlagscan be called multiple times on the same event and will overwrite the previously captured state. Other APIs such asStreamWaitEventuse the most recently captured state at the time of the API call, and are not affected by later calls toEventRecordWithFlags. Before the first call toEventRecordWithFlags, an event represents an empty set of work, so for exampleEventQuerywould returnCUDA_SUCCESS.flags include:
EVENT_RECORD_DEFAULT: Default event creation flag.EVENT_RECORD_EXTERNAL: Event is captured in the graph as an external event node when performing stream capture. This flag is invalid outside of stream capture.
- Parameters:
hEvent- event to recordhStream- stream to record event forflags- seeCUevent_capture_flags
-
cuEventQuery
public static int cuEventQuery(long hEvent) Queries an event's status.Queries the status of all work currently captured by
hEvent. SeeEventRecordfor details on what is captured by an event.Returns
CUDA_SUCCESSif all captured work has been completed, orCUDA_ERROR_NOT_READYif any captured work is incomplete.For the purposes of Unified Memory, a return value of
CUDA_SUCCESSis equivalent to having calledEventSynchronize.- Parameters:
hEvent- event to query
-
cuEventSynchronize
public static int cuEventSynchronize(long hEvent) Waits for an event to complete.Waits until the completion of all work currently captured in
hEvent. SeeEventRecordfor details on what is captured by an event.Waiting for an event that was created with the
EVENT_BLOCKING_SYNCflag will cause the calling CPU thread to block until the event has been completed by the device. If theEVENT_BLOCKING_SYNCflag has not been set, then the CPU thread will busy-wait until the event has been completed by the device.- Parameters:
hEvent- event to wait for
-
cuEventDestroy
public static int cuEventDestroy(long hEvent) Destroys an event.Destroys the event specified by
hEvent.An event may be destroyed before it is complete (i.e., while
EventQuerywould returnCUDA_ERROR_NOT_READY). In this case, the call does not block on completion of the event, and any associated resources will automatically be released asynchronously at completion.- Parameters:
hEvent- event to destroy
-
ncuEventElapsedTime
public static int ncuEventElapsedTime(long pMilliseconds, long hStart, long hEnd) Unsafe version of:EventElapsedTime -
cuEventElapsedTime
Computes the elapsed time between two events.Computes the elapsed time between two events (in milliseconds with a resolution of around 0.5 microseconds).
If either event was last recorded in a non-
NULLstream, the resulting time may be greater than expected (even if both used the same stream handle). This happens because theEventRecordoperation takes place asynchronously and there is no guarantee that the measured latency is actually just between the two events. Any number of other different stream operations could execute in between the two measured events, thus altering the timing in a significant way.If
EventRecordhas not been called on either event thenCUDA_ERROR_INVALID_HANDLEis returned. IfEventRecordhas been called on both events but one or both of them has not yet been completed (that is,EventQuerywould returnCUDA_ERROR_NOT_READYon at least one of the events),CUDA_ERROR_NOT_READYis returned. If either event was created with theEVENT_DISABLE_TIMINGflag, then this function will returnCUDA_ERROR_INVALID_HANDLE.- Parameters:
pMilliseconds- time betweenhStartandhEndin mshStart- starting eventhEnd- ending event
-
ncuImportExternalMemory
public static int ncuImportExternalMemory(long extMem_out, long memHandleDesc) Unsafe version of:ImportExternalMemory -
cuImportExternalMemory
public static int cuImportExternalMemory(PointerBuffer extMem_out, CUDA_EXTERNAL_MEMORY_HANDLE_DESC memHandleDesc) Imports an external memory object.Imports an externally allocated memory object and returns a handle to that in
extMem_out.The properties of the handle being imported must be described in
memHandleDesc.If
::typeisEXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FD, then::handle::fdmust be a valid file descriptor referencing a memory object. Ownership of the file descriptor is transferred to the CUDA driver when the handle is imported successfully. Performing any operations on the file descriptor after it is imported results in undefined behavior.If
::typeisEXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32, then exactly one of::handle::win32::handleand::handle::win32::namemust not beNULL. If::handle::win32::handleis notNULL, then it must represent a valid shared NT handle that references a memory object. Ownership of this handle is not transferred to CUDA after the import operation, so the application must release the handle using the appropriate system call. If::handle::win32::nameis not NULL, then it must point to a NULL-terminated array of UTF-16 characters that refers to a memory object.If
::typeisEXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_KMT, then::handle::win32::handlemust be non-NULLand::handle::win32::namemust beNULL. The handle specified must be a globally shared KMT handle. This handle does not hold a reference to the underlying object, and thus will be invalid when all references to the memory object are destroyed.If
::typeisEXTERNAL_MEMORY_HANDLE_TYPE_D3D12_HEAP, then exactly one of::handle::win32::handleand::handle::win32::namemust not beNULL. If::handle::win32::handleis notNULL, then it must represent a valid shared NT handle that is returned byID3D12Device::CreateSharedHandlewhen referring to aID3D12Heapobject. This handle holds a reference to the underlying object. If::handle::win32::nameis notNULL, then it must point to aNULL-terminated array of UTF-16 characters that refers to aID3D12Heapobject.If
::typeisEXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE, then exactly one of::handle::win32::handleand::handle::win32::namemust not be NULL. If::handle::win32::handleis notNULL, then it must represent a valid shared NT handle that is returned byID3D12Device::CreateSharedHandlewhen referring to aID3D12Resourceobject. This handle holds a reference to the underlying object. If::handle::win32::nameis notNULL, then it must point to aNULL-terminated array of UTF-16 characters that refers to aID3D12Resourceobject.If
::typeisEXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE, then::handle::win32::handlemust represent a valid shared NT handle that is\ returned byIDXGIResource1::CreateSharedHandlewhen referring to aID3D11Resourceobject. If::handle::win32::nameis notNULL, then it must point to aNULL-terminated array of UTF-16 characters that refers to aID3D11Resourceobject.If
::typeisEXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT, then::handle::win32::handlemust represent a valid shared KMT handle that is returned byIDXGIResource::GetSharedHandlewhen referring to aID3D11Resourceobject and::handle::win32::namemust beNULL.If
::typeisEXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF, then::handle::nvSciBufObjectmust be non-NULLand reference a validNvSciBufobject. If theNvSciBufobject imported into CUDA is also mapped by other drivers, then the application must useWaitExternalSemaphoresAsyncorSignalExternalSemaphoresAsyncas appropriate barriers to maintain coherence between CUDA and the other drivers. SeeCUDA_EXTERNAL_SEMAPHORE_SIGNAL_SKIP_NVSCIBUF_MEMSYNCandCUDA_EXTERNAL_SEMAPHORE_WAIT_SKIP_NVSCIBUF_MEMSYNCfor memory synchronization.The size of the memory object must be specified in
::size.Specifying the flag
CUDA_EXTERNAL_MEMORY_DEDICATEDin::flagsindicates that the resource is a dedicated resource. The definition of what a dedicated resource is outside the scope of this extension. This flag must be set if::typeis one of the following:EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCEEXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCEEXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT
Note
If the Vulkan memory imported into CUDA is mapped on the CPU then the application must use
vkInvalidateMappedMemoryRanges/vkFlushMappedMemoryRangesas well as appropriate Vulkan pipeline barriers to maintain coherence between CPU and GPU. For more information on these APIs, please refer to "Synchronization and Cache Control" chapter from Vulkan specification.- Parameters:
extMem_out- returned handle to an external memory objectmemHandleDesc- memory import handle descriptor
-
ncuExternalMemoryGetMappedBuffer
public static int ncuExternalMemoryGetMappedBuffer(long devPtr, long extMem, long bufferDesc) Unsafe version of:ExternalMemoryGetMappedBuffer -
cuExternalMemoryGetMappedBuffer
public static int cuExternalMemoryGetMappedBuffer(PointerBuffer devPtr, long extMem, CUDA_EXTERNAL_MEMORY_BUFFER_DESC bufferDesc) Maps a buffer onto an imported memory object.Maps a buffer onto an imported memory object and returns a device pointer in
devPtr.The properties of the buffer being mapped must be described in
bufferDesc.The offset and size have to be suitably aligned to match the requirements of the external API. Mapping two buffers whose ranges overlap may or may not result in the same virtual address being returned for the overlapped portion. In such cases, the application must ensure that all accesses to that region from the GPU are volatile. Otherwise writes made via one address are not guaranteed to be visible via the other address, even if they're issued by the same thread. It is recommended that applications map the combined range instead of mapping separate buffers and then apply the appropriate offsets to the returned pointer to derive the individual buffers.
The returned pointer
devPtrmust be freed usingMemFree.- Parameters:
devPtr- returned device pointer to bufferextMem- handle to external memory objectbufferDesc- buffer descriptor
-
ncuExternalMemoryGetMappedMipmappedArray
public static int ncuExternalMemoryGetMappedMipmappedArray(long mipmap, long extMem, long mipmapDesc) Unsafe version of:ExternalMemoryGetMappedMipmappedArray -
cuExternalMemoryGetMappedMipmappedArray
public static int cuExternalMemoryGetMappedMipmappedArray(PointerBuffer mipmap, long extMem, CUDA_EXTERNAL_MEMORY_MIPMAPPED_ARRAY_DESC mipmapDesc) Maps a CUDA mipmapped array onto an external memory object.Maps a CUDA mipmapped array onto an external object and returns a handle to it in
mipmap.The properties of the CUDA mipmapped array being mapped must be described in
mipmapDesc.::offsetis the offset in the memory object where the base level of the mipmap chain is.::arrayDescdescribes the format, dimensions and type of the base level of the mipmap chain. For further details on these parameters, please refer to the documentation forMipmappedArrayCreate. Note that if the mipmapped array is bound as a color target in the graphics API, then the flagCUDA_ARRAY3D_COLOR_ATTACHMENTmust be specified in::arrayDesc::Flags.::numLevelsspecifies the total number of levels in the mipmap chain.If
extMemwas imported from a handle of typeEXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF, then::numLevelsmust be equal to 1.The returned CUDA mipmapped array must be freed using
MipmappedArrayDestroy.- Parameters:
mipmap- returned CUDA mipmapped arrayextMem- handle to external memory objectmipmapDesc- CUDA array descriptor
-
cuDestroyExternalMemory
public static int cuDestroyExternalMemory(long extMem) Destroys an external memory object.Destroys the specified external memory object. Any existing buffers and CUDA mipmapped arrays mapped onto this object must no longer be used and must be explicitly freed using
MemFreeandMipmappedArrayDestroyrespectively.- Parameters:
extMem- external memory object to be destroyed
-
ncuImportExternalSemaphore
public static int ncuImportExternalSemaphore(long extSem_out, long semHandleDesc) Unsafe version of:ImportExternalSemaphore -
cuImportExternalSemaphore
public static int cuImportExternalSemaphore(PointerBuffer extSem_out, CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC semHandleDesc) Imports an external semaphore.Imports an externally allocated synchronization object and returns a handle to that in
extSem_out.The properties of the handle being imported must be described in
semHandleDesc.If
::typeisEXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD, then::handle::fdmust be a valid file descriptor referencing a synchronization object. Ownership of the file descriptor is transferred to the CUDA driver when the handle is imported successfully. Performing any operations on the file descriptor after it is imported results in undefined behavior.If
::typeisEXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32, then exactly one of::handle::win32::handleand::handle::win32::namemust not beNULL. If::handle::win32::handleis notNULL, then it must represent a valid shared NT handle that references a synchronization object. Ownership of this handle is not transferred to CUDA after the import operation, so the application must release the handle using the appropriate system call. If::handle::win32::nameis notNULL, then it must name a valid synchronization object.If
::typeisEXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT, then::handle::win32::handlemust be non-NULL and::handle::win32::namemust beNULL. The handle specified must be a globally shared KMT handle. This handle does not hold a reference to the underlying object, and thus will be invalid when all references to the synchronization object are destroyed.If
::typeisEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE, then exactly one of::handle::win32::handleand::handle::win32::namemust not beNULL. If::handle::win32::handleis notNULL, then it must represent a valid shared NT handle that is returned byID3D12Device::CreateSharedHandlewhen referring to aID3D12Fenceobject. This handle holds a reference to the underlying object. If::handle::win32::nameis notNULL, then it must name a valid synchronization object that refers to a validID3D12Fenceobject.If
::typeisEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE, then::handle::win32::handlerepresents a valid shared NT handle that is returned byID3D11Fence::CreateSharedHandle. If::handle::win32::nameis notNULL, then it must name a valid synchronization object that refers to a validID3D11Fenceobject.If
::typeisEXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC, then::handle::nvSciSyncObjrepresents a validNvSciSyncObj.EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX, then::handle::win32::handlerepresents a valid shared NT handle that is returned byIDXGIResource1::CreateSharedHandlewhen referring to aIDXGIKeyedMutexobject. If::handle::win32::nameis notNULL, then it must name a valid synchronization object that refers to a validIDXGIKeyedMutexobject.If
::typeisEXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT, then::handle::win32::handlerepresents a valid shared KMT handle that is returned byIDXGIResource::GetSharedHandlewhen referring to aIDXGIKeyedMutexobject and::handle::win32::namemust beNULL.If
::typeisEXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD, then::handle::fdmust be a valid file descriptor referencing a synchronization object. Ownership of the file descriptor is transferred to the CUDA driver when the handle is imported successfully. Performing any operations on the file descriptor after it is imported results in undefined behavior.If
::typeisEXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32, then exactly one of::handle::win32::handleand::handle::win32::namemust not beNULL. If::handle::win32::handleis notNULL, then it must represent a valid shared NT handle that references a synchronization object. Ownership of this handle is not transferred to CUDA after the import operation, so the application must release the handle using the appropriate system call. If::handle::win32::nameis notNULL, then it must name a valid synchronization object.- Parameters:
extSem_out- returned handle to an external semaphoresemHandleDesc- semaphore import handle descriptor
-
ncuSignalExternalSemaphoresAsync
public static int ncuSignalExternalSemaphoresAsync(long extSemArray, long paramsArray, int numExtSems, long stream) Unsafe version of:SignalExternalSemaphoresAsync- Parameters:
numExtSems- number of semaphores to signal
-
cuSignalExternalSemaphoresAsync
public static int cuSignalExternalSemaphoresAsync(PointerBuffer extSemArray, CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS.Buffer paramsArray, long stream) Signals a set of external semaphore objects,Enqueues a signal operation on a set of externally allocated semaphore object in the specified stream. The operations will be executed when all prior operations in the stream complete.
The exact semantics of signaling a semaphore depends on the type of the object.
If the semaphore object is any one of the following types:
EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD,EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32,EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMTthen signaling the semaphore will set it to the signaled state.If the semaphore object is any one of the following types:
EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE,EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE,EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD,EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32then the semaphore will be set to the value specified in::params::fence::value.If the semaphore object is of the type
EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNCthis API sets::params::nvSciSync::fenceto a value that can be used by subsequent waiters of the sameNvSciSyncobject to order operations with those currently submitted instream. Such an update will overwrite previous contents of::params::nvSciSync::fence. By default, signaling such an external semaphore object causes appropriate memory synchronization operations to be performed over all external memory objects that are imported asEXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF. This ensures that any subsequent accesses made by other importers of the same set of NvSciBuf memory object(s) are coherent. These operations can be skipped by specifying the flagCUDA_EXTERNAL_SEMAPHORE_SIGNAL_SKIP_NVSCIBUF_MEMSYNC, which can be used as a performance optimization when data coherency is not required. But specifying this flag in scenarios where data coherency is required results in undefined behavior. Also, for semaphore object of the typeEXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC, if theNvSciSyncAttrListused to create theNvSciSyncObjhad not set the flags inDeviceGetNvSciSyncAttributestoCUDA_NVSCISYNC_ATTR_SIGNAL, this API will returnCUDA_ERROR_NOT_SUPPORTED.If the semaphore object is any one of the following types:
EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX,EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMTthen the keyed mutex will be released with the key specified in::params::keyedmutex::key.- Parameters:
extSemArray- set of external semaphores to be signaledparamsArray- array of semaphore parametersstream- stream to enqueue the signal operations in
-
ncuWaitExternalSemaphoresAsync
public static int ncuWaitExternalSemaphoresAsync(long extSemArray, long paramsArray, int numExtSems, long stream) Unsafe version of:WaitExternalSemaphoresAsync- Parameters:
numExtSems- number of semaphores to wait on
-
cuWaitExternalSemaphoresAsync
public static int cuWaitExternalSemaphoresAsync(PointerBuffer extSemArray, CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS.Buffer paramsArray, long stream) Waits on a set of external semaphore objects.Enqueues a wait operation on a set of externally allocated semaphore object in the specified stream. The operations will be executed when all prior operations in the stream complete.
The exact semantics of waiting on a semaphore depends on the type of the object.
If the semaphore object is any one of the following types:
EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD,EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32,EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMTthen waiting on the semaphore will wait until the semaphore reaches the signaled state. The semaphore will then be reset to the unsignaled state. Therefore for every signal operation, there can only be one wait operation.If the semaphore object is any one of the following types:
EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE,EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE,EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD,EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32then waiting on the semaphore will wait until the value of the semaphore is greater than or equal to::params::fence::value.If the semaphore object is of the type
EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNCthen, waiting on the semaphore will wait until the::params::nvSciSync::fenceis signaled by the signaler of the NvSciSyncObj that was associated with this semaphore object. By default, waiting on such an external semaphore object causes appropriate memory synchronization operations to be performed over all external memory objects that are imported asEXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF. This ensures that any subsequent accesses made by other importers of the same set ofNvSciBufmemory object(s) are coherent. These operations can be skipped by specifying the flagCUDA_EXTERNAL_SEMAPHORE_WAIT_SKIP_NVSCIBUF_MEMSYNC, which can be used as a performance optimization when data coherency is not required. But specifying this flag in scenarios where data coherency is required results in undefined behavior. Also, for semaphore object of the typeEXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC, if theNvSciSyncAttrListused to create theNvSciSyncObjhad not set the flags inDeviceGetNvSciSyncAttributestoCUDA_NVSCISYNC_ATTR_WAIT, this API will returnCUDA_ERROR_NOT_SUPPORTED.If the semaphore object is any one of the following types:
EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX,EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMTthen the keyed mutex will be acquired when it is released with the key specified in::params::keyedmutex::keyor until the timeout specified by::params::keyedmutex::timeoutMshas lapsed. The timeout interval can either be a finite value specified in milliseconds or an infinite value. In case an infinite value is specified the timeout never elapses. The windowsINFINITEmacro must be used to specify infinite timeout.- Parameters:
extSemArray- external semaphores to be waited onparamsArray- array of semaphore parametersstream- stream to enqueue the wait operations in
-
cuDestroyExternalSemaphore
public static int cuDestroyExternalSemaphore(long extSem) Destroys an external semaphore.Destroys an external semaphore object and releases any references to the underlying resource. Any outstanding signals or waits must have completed before the semaphore is destroyed.
- Parameters:
extSem- external semaphore to be destroyed
-
cuStreamWaitValue32
public static int cuStreamWaitValue32(long stream, long addr, int value, int flags) Wait on a memory location.Enqueues a synchronization of the stream on the given memory location. Work ordered after the operation will block until the given condition on the memory is satisfied. By default, the condition is to wait for
(int32_t)(*addr - value) >= 0, a cyclic greater-or-equal. Other condition types can be specified viaflags.If the memory was registered via
MemHostRegister, the device pointer should be obtained withMemHostGetDevicePointer. This function cannot be used with managed memory (MemAllocManaged).Support for this can be queried with
DeviceGetAttributeandDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS.Support for
STREAM_WAIT_VALUE_NORcan be queried withDeviceGetAttributeandDEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR.- Parameters:
stream- the stream to synchronize on the memory locationaddr- the memory location to wait onvalue- the value to compare with the memory locationflags- seeCUstreamWaitValue_flags
-
cuStreamWaitValue64
public static int cuStreamWaitValue64(long stream, long addr, long value, int flags) Wait on a memory location.Enqueues a synchronization of the stream on the given memory location. Work ordered after the operation will block until the given condition on the memory is satisfied. By default, the condition is to wait for
(int64_t)(*addr - value) >= 0, a cyclic greater-or-equal. Other condition types can be specified viaflags.If the memory was registered via
MemHostRegister, the device pointer should be obtained withMemHostGetDevicePointer.Support for this can be queried with
DeviceGetAttributeandDEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS.- Parameters:
stream- the stream to synchronize on the memory locationaddr- the memory location to wait onvalue- the value to compare with the memory locationflags- seeCUstreamWaitValue_flags
-
cuStreamWriteValue32
public static int cuStreamWriteValue32(long stream, long addr, int value, int flags) Write a value to memory.Write a value to memory. Unless the
STREAM_WRITE_VALUE_NO_MEMORY_BARRIERflag is passed, the write is preceded by a system-wide memory fence, equivalent to a__threadfence_system()but scoped to the stream rather than a CUDA thread.If the memory was registered via
MemHostRegister, the device pointer should be obtained withMemHostGetDevicePointer. This function cannot be used with managed memory (MemAllocManaged).Support for this can be queried with
DeviceGetAttributeandDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS.- Parameters:
stream- the stream to do the write inaddr- the device address to write tovalue- the value to writeflags- seeCUstreamWriteValue_flags
-
cuStreamWriteValue64
public static int cuStreamWriteValue64(long stream, long addr, long value, int flags) Write a value to memory.Write a value to memory. Unless the
STREAM_WRITE_VALUE_NO_MEMORY_BARRIERflag is passed, the write is preceded by a system-wide memory fence, equivalent to a__threadfence_system()but scoped to the stream rather than a CUDA thread.If the memory was registered via
MemHostRegister, the device pointer should be obtained withMemHostGetDevicePointer.Support for this can be queried with
DeviceGetAttributeandDEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS.- Parameters:
stream- the stream to do the write inaddr- the device address to write tovalue- the value to writeflags- seeCUstreamWriteValue_flags
-
ncuStreamBatchMemOp
public static int ncuStreamBatchMemOp(long stream, int count, long paramArray, int flags) Unsafe version of:StreamBatchMemOp- Parameters:
count- the number of operations in the array. Must be less than 256.
-
cuStreamBatchMemOp
public static int cuStreamBatchMemOp(long stream, CUstreamBatchMemOpParams.Buffer paramArray, int flags) Batch operations to synchronize the stream via memory operations.This is a batch version of
StreamWaitValue32andStreamWriteValue32. Batching operations may avoid some performance overhead in both the API call and the device execution versus adding them to the stream in separate API calls. The operations are enqueued in the order they appear in the array.See
CUstreamBatchMemOpTypefor the full set of supported operations, andStreamWaitValue32,StreamWaitValue64,StreamWriteValue32, andStreamWriteValue64for details of specific operations.Basic support for this can be queried with
DeviceGetAttributeandDEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS. See related APIs for details on querying support for specific operations.- Parameters:
stream- the stream to enqueue the operations inparamArray- the types and parameters of the individual operationsflags- reserved for future expansion; must be 0
-
ncuFuncGetAttribute
public static int ncuFuncGetAttribute(long pi, int attrib, long hfunc) Unsafe version of:FuncGetAttribute -
cuFuncGetAttribute
Returns information about a function.Returns in
*pithe integer value of the attributeattribon the kernel given byhfunc. The supported attributes are:FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK: The maximum number of threads per block, beyond which a launch of the function would fail. This number depends on both the function and the device on which the function is currently loaded.FUNC_ATTRIBUTE_SHARED_SIZE_BYTES: The size in bytes of statically-allocated shared memory per block required by this function. This does not include dynamically-allocated shared memory requested by the user at runtime.FUNC_ATTRIBUTE_CONST_SIZE_BYTES: The size in bytes of user-allocated constant memory required by this function.FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES: The size in bytes of local memory used by each thread of this function.FUNC_ATTRIBUTE_NUM_REGS: The number of registers used by each thread of this function.FUNC_ATTRIBUTE_PTX_VERSION: The PTX virtual architecture version for which the function was compiled. This value is the major PTX version * 10 + the minor PTX version, so a PTX version 1.3 function would return the value 13. Note that this may return the undefined value of 0 for cubins compiled prior to CUDA 3.0.FUNC_ATTRIBUTE_BINARY_VERSION: The binary architecture version for which the function was compiled. This value is the major binary version * 10 + the minor binary version, so a binary version 1.3 function would return the value 13. Note that this will return a value of 10 for legacy cubins that do not have a properly-encoded binary architecture version.FUNC_ATTRIBUTE_CACHE_MODE_CA: The attribute to indicate whether the function has been compiled with user specified option "-Xptxas --dlcm=ca" set.FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES: The maximum size in bytes of dynamically-allocated shared memory.FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT: Preferred shared memory-L1 cache split ratio in percent of total shared memory.
- Parameters:
pi- returned attribute valueattrib- attribute requestedhfunc- function to query attribute of
-
cuFuncSetAttribute
public static int cuFuncSetAttribute(long hfunc, int attrib, int value) Sets information about a function.This call sets the value of a specified attribute
attribon the kernel given byhfuncto an integer value specified byvalThis function returnsCUDA_SUCCESSif the new value of the attribute could be successfully set. If the set fails, this call will return an error. Not all attributes can have values set. Attempting to set a value on a read-only attribute will result in an error (CUDA_ERROR_INVALID_VALUE).Supported attributes for the cuFuncSetAttribute call are:
FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES: This maximum size in bytes of dynamically-allocated shared memory. The value should contain the requested maximum size of dynamically-allocated shared memory. The sum of this value and the function attributeFUNC_ATTRIBUTE_SHARED_SIZE_BYTEScannot exceed the device attributeDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN. The maximal size of requestable dynamic shared memory may differ by GPU architecture.FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT: On devices where the L1 cache and shared memory use the same hardware resources, this sets the shared memory carveout preference, in percent of the total shared memory. SeeDEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSORThis is only a hint, and the driver can choose a different ratio if required to execute the function.
- Parameters:
hfunc- function to query attribute ofattrib- attribute requestedvalue- the value to set
-
cuFuncSetCacheConfig
public static int cuFuncSetCacheConfig(long hfunc, int config) Sets the preferred cache configuration for a device function.On devices where the L1 cache and shared memory use the same hardware resources, this sets through
configthe preferred cache configuration for the device functionhfunc. This is only a preference. The driver will use the requested configuration if possible, but it is free to choose a different configuration if required to executehfunc. Any context-wide preference set viaCtxSetCacheConfigwill be overridden by this per-function setting unless the per-function setting isFUNC_CACHE_PREFER_NONE. In that case, the current context-wide setting will be used.This setting does nothing on devices where the size of the L1 cache and shared memory are fixed.
Launching a kernel with a different preference than the most recent preference setting may insert a device-side synchronization point.
The supported cache configurations are:
FUNC_CACHE_PREFER_NONE: no preference for shared memory or L1 (default)FUNC_CACHE_PREFER_SHARED: prefer larger shared memory and smaller L1 cacheFUNC_CACHE_PREFER_L1: prefer larger L1 cache and smaller shared memoryFUNC_CACHE_PREFER_EQUAL: prefer equal sized L1 cache and shared memory
- Parameters:
hfunc- kernel to configure cache forconfig- requested cache configuration
-
ncuFuncGetModule
public static int ncuFuncGetModule(long hmod, long hfunc) Unsafe version of:FuncGetModule -
cuFuncGetModule
Returns a module handle.Returns in
*hmodthe handle of the module that functionhfuncis located in. The lifetime of the module corresponds to the lifetime of the context it was loaded in or until the module is explicitly unloaded.The CUDA runtime manages its own modules loaded into the primary context. If the handle returned by this API refers to a module loaded by the CUDA runtime, calling
ModuleUnloadon that module will result in undefined behavior.- Parameters:
hmod- returned module handlehfunc- function to retrieve module for
-
ncuLaunchKernel
public static int ncuLaunchKernel(long f, int gridDimX, int gridDimY, int gridDimZ, int blockDimX, int blockDimY, int blockDimZ, int sharedMemBytes, long hStream, long kernelParams, long extra) Unsafe version of:LaunchKernel -
cuLaunchKernel
public static int cuLaunchKernel(long f, int gridDimX, int gridDimY, int gridDimZ, int blockDimX, int blockDimY, int blockDimZ, int sharedMemBytes, long hStream, @Nullable PointerBuffer kernelParams, @Nullable PointerBuffer extra) Launches a CUDA function.Invokes the kernel
fon agridDimXxgridDimYxgridDimZgrid of blocks. Each block containsblockDimXxblockDimYxblockDimZthreads.sharedMemBytessets the amount of dynamic shared memory that will be available to each thread block.Kernel parameters to
fcan be specified in one of two ways:- Kernel parameters can be specified via
kernelParams.If
fhas N parameters, thenkernelParamsneeds to be an array of N pointers. Each ofkernelParams[0]throughkernelParams[N-1]must point to a region of memory from which the actual kernel parameter will be copied. The number of kernel parameters and their offsets and sizes do not need to be specified as that information is retrieved directly from the kernel's image. - Kernel parameters can also be packaged by the application into a single buffer that is passed in via the
extraparameter.This places the burden on the application of knowing each kernel parameter's size and alignment/padding within the buffer. Here is an example of using the
extraparameter in this manner:size_t argBufferSize; char argBuffer[256]; // populate argBuffer and argBufferSize void *config[] = { CU_LAUNCH_PARAM_BUFFER_POINTER, argBuffer, CU_LAUNCH_PARAM_BUFFER_SIZE, &argBufferSize, CU_LAUNCH_PARAM_END }; status = cuLaunchKernel(f, gx, gy, gz, bx, by, bz, sh, s, NULL, config);
The
extraparameter exists to allowcuLaunchKernel()to take additional less commonly used arguments.extraspecifies a list of names of extra settings and their corresponding values. Each extra setting name is immediately followed by the corresponding value. The list must be terminated with eitherNULLorLAUNCH_PARAM_END.LAUNCH_PARAM_END, which indicates the end of theextraarrayLAUNCH_PARAM_BUFFER_POINTER, which specifies that the next value inextrawill be a pointer to a buffer containing all the kernel parameters for launching kernelfLAUNCH_PARAM_BUFFER_SIZE, which specifies that the next value inextrawill be a pointer to a size_t containing the size of the buffer specified withLAUNCH_PARAM_BUFFER_POINTER
The error
CUDA_ERROR_INVALID_VALUEwill be returned if kernel parameters are specified with bothkernelParamsandextra(i.e. bothkernelParamsandextraare non-NULL).Calling
cuLaunchKernel()invalidates the persistent function state set through the following deprecated APIs:FuncSetBlockShape,FuncSetSharedSize,ParamSetSize,ParamSeti,ParamSetf,ParamSetv.Note that to use
LaunchKernel, the kernelfmust either have been compiled with toolchain version 3.2 or later so that it will contain kernel parameter information, or have no kernel parameters. If either of these conditions is not met, thenLaunchKernelwill returnCUDA_ERROR_INVALID_IMAGE.- Parameters:
f- kernel to launchgridDimX- width of grid in blocksgridDimY- height of grid in blocksgridDimZ- depth of grid in blocksblockDimX- x dimension of each thread blockblockDimY- y dimension of each thread blockblockDimZ- z dimension of each thread blocksharedMemBytes- dynamic shared-memory size per thread block in byteshStream- stream identifierkernelParams- array of pointers to kernel parametersextra- extra options
- Kernel parameters can be specified via
-
ncuLaunchCooperativeKernel
public static int ncuLaunchCooperativeKernel(long f, int gridDimX, int gridDimY, int gridDimZ, int blockDimX, int blockDimY, int blockDimZ, int sharedMemBytes, long hStream, long kernelParams) Unsafe version of:LaunchCooperativeKernel -
cuLaunchCooperativeKernel
public static int cuLaunchCooperativeKernel(long f, int gridDimX, int gridDimY, int gridDimZ, int blockDimX, int blockDimY, int blockDimZ, int sharedMemBytes, long hStream, @Nullable PointerBuffer kernelParams) Launches a CUDA function where thread blocks can cooperate and synchronize as they execute.Invokes the kernel
fon agridDimXxgridDimYxgridDimZgrid of blocks. Each block containsblockDimXxblockDimYxblockDimZthreads.sharedMemBytessets the amount of dynamic shared memory that will be available to each thread block.The device on which this kernel is invoked must have a non-zero value for the device attribute
DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH.The total number of blocks launched cannot exceed the maximum number of blocks per multiprocessor as returned by
OccupancyMaxActiveBlocksPerMultiprocessor(orOccupancyMaxActiveBlocksPerMultiprocessorWithFlags) times the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.The kernel cannot make use of CUDA dynamic parallelism.
Kernel parameters must be specified via
kernelParams. Iffhas N parameters, thenkernelParamsneeds to be an array of N pointers. Each ofkernelParams[0]throughkernelParams[N-1]must point to a region of memory from which the actual kernel parameter will be copied. The number of kernel parameters and their offsets and sizes do not need to be specified as that information is retrieved directly from the kernel's image.Calling
LaunchCooperativeKernelsets persistent function state that is the same as function state set throughLaunchKernelAPIWhen the kernel
fis launched viaLaunchCooperativeKernel, the previous block shape, shared size and parameter info associated withfis overwritten.Note that to use
LaunchCooperativeKernel, the kernelfmust either have been compiled with toolchain version 3.2 or later so that it will contain kernel parameter information, or have no kernel parameters. If either of these conditions is not met, thenLaunchCooperativeKernelwill returnCUDA_ERROR_INVALID_IMAGE.- Parameters:
f- kernel to launchgridDimX- width of grid in blocksgridDimY- height of grid in blocksgridDimZ- depth of grid in blocksblockDimX- x dimension of each thread blockblockDimY- y dimension of each thread blockblockDimZ- z dimension of each thread blocksharedMemBytes- dynamic shared-memory size per thread block in byteshStream- stream identifierkernelParams- array of pointers to kernel parameters
-
ncuLaunchCooperativeKernelMultiDevice
public static int ncuLaunchCooperativeKernelMultiDevice(long launchParamsList, int numDevices, int flags) Unsafe version of:LaunchCooperativeKernelMultiDevice- Parameters:
numDevices- size of thelaunchParamsListarray
-
cuLaunchCooperativeKernelMultiDevice
public static int cuLaunchCooperativeKernelMultiDevice(CUDA_LAUNCH_PARAMS.Buffer launchParamsList, int flags) Launches CUDA functions on multiple devices where thread blocks can cooperate and synchronize as they executeDeprecated: This function is deprecated as of CUDA 11.3.Invokes kernels as specified in the
launchParamsListarray where each element of the array specifies all the parameters required to perform a single kernel launch. These kernels can cooperate and synchronize as they execute. The size of the array is specified bynumDevices.No two kernels can be launched on the same device. All the devices targeted by this multi-device launch must be identical. All devices must have a non-zero value for the device attribute
DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH.All kernels launched must be identical with respect to the compiled code. Note that any __device__ __constant__ or __managed__ variables present in the module that owns the kernel launched on each device, are independently instantiated on every device. It is the application's responsibility to ensure these variables are initialized and used appropriately.
The size of the grids as specified in blocks, the size of the blocks themselves and the amount of shared memory used by each thread block must also match across all launched kernels.
The streams used to launch these kernels must have been created via either
StreamCreateorStreamCreateWithPriority. TheNULLstream orSTREAM_LEGACYorSTREAM_PER_THREADcannot be used.The total number of blocks launched per kernel cannot exceed the maximum number of blocks per multiprocessor as returned by
OccupancyMaxActiveBlocksPerMultiprocessor(orOccupancyMaxActiveBlocksPerMultiprocessorWithFlags) times the number of multiprocessors as specified by the device attributeDEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT. Since the total number of blocks launched per device has to match across all devices, the maximum number of blocks that can be launched per device will be limited by the device with the least number of multiprocessors.The kernels cannot make use of CUDA dynamic parallelism.
CUDA_LAUNCH_PARAMS::functionspecifies the kernel to be launched. All functions must be identical with respect to the compiled code.CUDA_LAUNCH_PARAMS::gridDimXis the width of the grid in blocks. This must match across all kernels launched.CUDA_LAUNCH_PARAMS::gridDimYis the height of the grid in blocks. This must match across all kernels launched.CUDA_LAUNCH_PARAMS::gridDimZis the depth of the grid in blocks. This must match across all kernels launched.CUDA_LAUNCH_PARAMS::blockDimXis the X dimension of each thread block. This must match across all kernels launched.CUDA_LAUNCH_PARAMS::blockDimXis the Y dimension of each thread block. This must match across all kernels launched.CUDA_LAUNCH_PARAMS::blockDimZis the Z dimension of each thread block. This must match across all kernels launched.CUDA_LAUNCH_PARAMS::sharedMemBytesis the dynamic shared-memory size per thread block in bytes. This must match across all kernels launched.CUDA_LAUNCH_PARAMS::hStreamis the handle to the stream to perform the launch in. This cannot be theNULLstream orSTREAM_LEGACYorSTREAM_PER_THREAD. The CUDA context associated with this stream must match that associated withCUDA_LAUNCH_PARAMS::function.CUDA_LAUNCH_PARAMS::kernelParamsis an array of pointers to kernel parameters. If::functionhas N parameters, then::kernelParamsneeds to be an array of N pointers. Each of::kernelParams[0]through::kernelParams[N-1]must point to a region of memory from which the actual kernel parameter will be copied. The number of kernel parameters and their offsets and sizes do not need to be specified as that information is retrieved directly from the kernel's image.
By default, the kernel won't begin execution on any GPU until all prior work in all the specified streams has completed. This behavior can be overridden by specifying the flag
CUDA_COOPERATIVE_LAUNCH_MULTI_DEVICE_NO_PRE_LAUNCH_SYNC. When this flag is specified, each kernel will only wait for prior work in the stream corresponding to that GPU to complete before it begins execution.Similarly, by default, any subsequent work pushed in any of the specified streams will not begin execution until the kernels on all GPUs have completed. This behavior can be overridden by specifying the flag
CUDA_COOPERATIVE_LAUNCH_MULTI_DEVICE_NO_POST_LAUNCH_SYNC. When this flag is specified, any subsequent work pushed in any of the specified streams will only wait for the kernel launched on the GPU corresponding to that stream to complete before it begins execution.Calling
LaunchCooperativeKernelMultiDevicesets persistent function state that is the same as function state set throughLaunchKernelAPI when called individually for each element inlaunchParamsList.When kernels are launched via
LaunchCooperativeKernelMultiDevice, the previous block shape, shared size and parameter info associated with eachCUDA_LAUNCH_PARAMS::functioninlaunchParamsListis overwritten.Note that to use
LaunchCooperativeKernelMultiDevice, the kernels must either have been compiled with toolchain version 3.2 or later so that it will contain kernel parameter information, or have no kernel parameters. If either of these conditions is not met, thenLaunchCooperativeKernelMultiDevicewill returnCUDA_ERROR_INVALID_IMAGE.- Parameters:
launchParamsList- list of launch parameters, one per deviceflags- flags to control launch behavior
-
ncuLaunchHostFunc
public static int ncuLaunchHostFunc(long hStream, long fn, long userData) Unsafe version of:LaunchHostFunc -
cuLaunchHostFunc
Enqueues a host function call in a stream.Enqueues a host function to run in a stream. The function will be called after currently enqueued work and will block work added after it.
The host function must not make any CUDA API calls. Attempting to use a CUDA API may result in
CUDA_ERROR_NOT_PERMITTED, but this is not required. The host function must not perform any synchronization that may depend on outstanding CUDA work not mandated to run earlier. Host functions without a mandated order (such as in independent streams) execute in undefined order and may be serialized.For the purposes of Unified Memory, execution makes a number of guarantees:
- The stream is considered idle for the duration of the function's execution. Thus, for example, the function may always use memory attached to the stream it was enqueued in.
- The start of execution of the function has the same effect as synchronizing an event recorded in the same stream immediately prior to the function. It thus synchronizes streams which have been "joined" prior to the function.
- Adding device work to any stream does not have the effect of making the stream active until all preceding host functions and stream callbacks have executed. Thus, for example, a function might use global attached memory even if work has been added to another stream, if the work has been ordered behind the function call with an event.
- Completion of the function does not cause a stream to become active except as described above. The stream will remain idle if no device work follows the function, and will remain idle across consecutive host functions or stream callbacks without device work in between. Thus, for example, stream synchronization can be done by signaling from a host function at the end of the stream.
Note that, in contrast to
StreamAddCallback, the function will not be called in the event of an error in the CUDA context.- Parameters:
hStream- stream to enqueue function call infn- the function to call once preceding stream operations are completeuserData- user-specified data to be passed to the function
-
cuFuncSetBlockShape
public static int cuFuncSetBlockShape(long hfunc, int x, int y, int z) Sets the block-dimensions for the function. (Deprecated)Specifies the
x,y, andzdimensions of the thread blocks that are created when the kernel given byhfuncis launched.- Parameters:
hfunc- kernel to specify dimensions ofx- x dimensiony- y dimensionz- z dimension
-
cuParamSetSize
public static int cuParamSetSize(long hfunc, int numbytes) Sets the parameter size for the function. (Deprecated)Sets through
numbytesthe total size in bytes needed by the function parameters of the kernel corresponding tohfunc.- Parameters:
hfunc- kernel to set parameter size fornumbytes- size of parameter list in bytes
-
cuParamSeti
public static int cuParamSeti(long hfunc, int offset, int value) Adds an integer parameter to the function's argument listDeprecated:Sets an integer parameter that will be specified the next time the kernel corresponding to
hfuncwill be invoked.offsetis a byte offset.- Parameters:
hfunc- kernel to add parameter tooffset- offset to add parameter to argument listvalue- value of parameter
-
cuParamSetf
public static int cuParamSetf(long hfunc, int offset, float value) Adds a floating-point parameter to the function's argument list. (Deprecated)Sets a floating-point parameter that will be specified the next time the kernel corresponding to
hfuncwill be invoked.offsetis a byte offset.- Parameters:
hfunc- kernel to add parameter tooffset- offset to add parameter to argument listvalue- value of parameter
-
ncuParamSetv
public static int ncuParamSetv(long hfunc, int offset, long ptr, int numbytes) Unsafe version of:ParamSetv- Parameters:
numbytes- size of data to copy in bytes
-
cuParamSetv
Adds arbitrary data to the function's argument list. (Deprecated)Copies an arbitrary amount of data (specified in
numbytes) fromptrinto the parameter space of the kernel corresponding tohfunc.offsetis a byte offset.- Parameters:
hfunc- kernel to add data tooffset- offset to add data to argument listptr- pointer to arbitrary data
-
cuLaunch
public static int cuLaunch(long f) Launches a CUDA function. (Deprecated)Invokes the kernel
fon a 1 x 1 x 1 grid of blocks. The block contains the number of threads specified by a previous call toFuncSetBlockShape.The block shape, dynamic shared memory size, and parameter information must be set using
FuncSetBlockShape,FuncSetSharedSize,ParamSetSize,ParamSeti,ParamSetf, andParamSetvprior to calling this function.Launching a function via
LaunchKernelinvalidates the function's block shape, dynamic shared memory size, and parameter information. After launching via cuLaunchKernel, this state must be re-initialized prior to calling this function. Failure to do so results in undefined behavior.- Parameters:
f- kernel to launch
-
cuLaunchGrid
public static int cuLaunchGrid(long f, int grid_width, int grid_height) Launches a CUDA function. (Deprecated)Invokes the kernel
fon agrid_widthxgrid_heightgrid of blocks. Each block contains the number of threads specified by a previous call toFuncSetBlockShape.The block shape, dynamic shared memory size, and parameter information must be set using
FuncSetBlockShape,FuncSetSharedSize,ParamSetSize,ParamSeti,ParamSetf, andParamSetvprior to calling this function.Launching a function via
LaunchKernelinvalidates the function's block shape, dynamic shared memory size, and parameter information. After launching via cuLaunchKernel, this state must be re-initialized prior to calling this function. Failure to do so results in undefined behavior.- Parameters:
f- kernel to launchgrid_width- width of grid in blocksgrid_height- height of grid in blocks
-
cuLaunchGridAsync
public static int cuLaunchGridAsync(long f, int grid_width, int grid_height, long hStream) Launches a CUDA function. (Deprecated)Invokes the kernel
fon agrid_widthxgrid_heightgrid of blocks. Each block contains the number of threads specified by a previous call toFuncSetBlockShape.The block shape, dynamic shared memory size, and parameter information must be set using
FuncSetBlockShape,FuncSetSharedSize,ParamSetSize,ParamSeti,ParamSetf, andParamSetvprior to calling this function.Launching a function via
LaunchKernelinvalidates the function's block shape, dynamic shared memory size, and parameter information. After launching via cuLaunchKernel, this state must be re-initialized prior to calling this function. Failure to do so results in undefined behavior.Note
In certain cases where cubins are created with no ABI (i.e., using
ptxas--abi-compileno), this function may serialize kernel launches. The CUDA driver retains asynchronous behavior by growing the per-thread stack as needed per launch and not shrinking it afterwards.- Parameters:
f- kernel to launchgrid_width- width of grid in blocksgrid_height- height of grid in blockshStream- stream identifier
-
cuParamSetTexRef
public static int cuParamSetTexRef(long hfunc, int texunit, long hTexRef) Adds a texture-reference to the function's argument list. (Deprecated)Makes the CUDA array or linear memory bound to the texture reference
hTexRefavailable to a device program as a texture. In this version of CUDA, the texture-reference must be obtained viaModuleGetTexRefand thetexunitparameter must be set toPARAM_TR_DEFAULT.- Parameters:
hfunc- kernel to add texture-reference totexunit- texture unit (must bePARAM_TR_DEFAULT)hTexRef- texture-reference to add to argument list
-
ncuGraphCreate
public static int ncuGraphCreate(long phGraph, int flags) Unsafe version of:GraphCreate -
cuGraphCreate
Creates a graph.Creates an empty graph, which is returned via
phGraph.- Parameters:
phGraph- returns newly created graphflags- graph creation flags, must be 0
-
ncuGraphAddKernelNode
public static int ncuGraphAddKernelNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long nodeParams) Unsafe version of:GraphAddKernelNode- Parameters:
numDependencies- number of dependencies
-
cuGraphAddKernelNode
public static int cuGraphAddKernelNode(PointerBuffer phGraphNode, long hGraph, @Nullable PointerBuffer dependencies, CUDA_KERNEL_NODE_PARAMS nodeParams) Creates a kernel execution node and adds it to a graph.Creates a new kernel execution node and adds it to
hGraphwithnumDependenciesdependencies specified viadependenciesand arguments specified innodeParams. It is possible fornumDependenciesto be 0, in which case the node will be placed at the root of the graph.dependenciesmay not have any duplicate entries. A handle to the new node will be returned inphGraphNode.When the graph is launched, the node will invoke kernel
funcon a (gridDimXxgridDimYxgridDimZ) grid of blocks. Each block contains (blockDimXxblockDimYxblockDimZ) threads.sharedMemBytessets the amount of dynamic shared memory that will be available to each thread block.Kernel parameters to
funccan be specified in one of two ways:- Kernel parameters can be specified via
kernelParams. If the kernel has N parameters, thenkernelParamsneeds to be an array of N pointers. Each pointer, fromkernelParams[0]tokernelParams[N-1], points to the region of memory from which the actual parameter will be copied. The number of kernel parameters and their offsets and sizes do not need to be specified as that information is retrieved directly from the kernel's image. - Kernel parameters for non-cooperative kernels can also be packaged by the application into a single buffer that is passed in via
extra. This places the burden on the application of knowing each kernel parameter's size and alignment/padding within the buffer. Theextraparameter exists to allow this function to take additional less commonly used arguments.extraspecifies a list of names of extra settings and their corresponding values. Each extra setting name is immediately followed by the corresponding value. The list must be terminated with eitherNULLorLAUNCH_PARAM_END.LAUNCH_PARAM_END, which indicates the end of theextraarray;LAUNCH_PARAM_BUFFER_POINTER, which specifies that the next value inextrawill be a pointer to a buffer containing all the kernel parameters for launching kernelfunc;LAUNCH_PARAM_BUFFER_SIZE, which specifies that the next value inextrawill be a pointer to a size_t containing the size of the buffer specified withLAUNCH_PARAM_BUFFER_POINTER;
The error
CUDA_ERROR_INVALID_VALUEwill be returned if kernel parameters are specified with bothkernelParamsandextra(i.e. bothkernelParamsandextraare non-NULL).CUDA_ERROR_INVALID_VALUEwill be returned ifextrais used for a cooperative kernel.The
kernelParamsorextraarray, as well as the argument values it points to, are copied during this call.Note
Kernels launched using graphs must not use texture and surface references. Reading or writing through any texture or surface reference is undefined behavior. This restriction does not apply to texture and surface objects.
- Parameters:
phGraphNode- returns newly created nodehGraph- graph to which to add the nodedependencies- dependencies of the nodenodeParams- parameters for the GPU execution node
- Kernel parameters can be specified via
-
ncuGraphKernelNodeGetParams
public static int ncuGraphKernelNodeGetParams(long hNode, long nodeParams) Unsafe version of:GraphKernelNodeGetParams -
cuGraphKernelNodeGetParams
Returns a kernel node's parameters.Returns the parameters of kernel node
hNodeinnodeParams. ThekernelParamsorextraarray returned innodeParams, as well as the argument values it points to, are owned by the node. This memory remains valid until the node is destroyed or its parameters are modified, and should not be modified directly. UseGraphKernelNodeSetParamsto update the parameters of this node.The params will contain either
kernelParamsorextra, according to which of these was most recently set on the node.- Parameters:
hNode- node to get the parameters fornodeParams- pointer to return the parameters
-
ncuGraphKernelNodeSetParams
public static int ncuGraphKernelNodeSetParams(long hNode, long nodeParams) Unsafe version of:GraphKernelNodeSetParams -
cuGraphKernelNodeSetParams
Sets a kernel node's parameters.Sets the parameters of kernel node
hNodetonodeParams.- Parameters:
hNode- node to set the parameters fornodeParams- parameters to copy
-
ncuGraphAddMemcpyNode
public static int ncuGraphAddMemcpyNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long copyParams, long ctx) Unsafe version of:GraphAddMemcpyNode- Parameters:
numDependencies- number of dependencies
-
cuGraphAddMemcpyNode
public static int cuGraphAddMemcpyNode(PointerBuffer phGraphNode, long hGraph, @Nullable PointerBuffer dependencies, CUDA_MEMCPY3D copyParams, long ctx) Creates a memcpy node and adds it to a graph.Creates a new memcpy node and adds it to
hGraphwithnumDependenciesdependencies specified viadependencies. It is possible fornumDependenciesto be 0, in which case the node will be placed at the root of the graph.dependenciesmay not have any duplicate entries. A handle to the new node will be returned inphGraphNode.When the graph is launched, the node will perform the memcpy described by
copyParams. SeeMemcpy3Dfor a description of the structure and its restrictions.Memcpy nodes have some additional restrictions with regards to managed memory, if the system contains at least one device which has a zero value for the device attribute
DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS. If one or more of the operands refer to managed memory, then using the memory typeMEMORYTYPE_UNIFIEDis disallowed for those operand(s). The managed memory will be treated as residing on either the host or the device, depending on which memory type is specified.- Parameters:
phGraphNode- returns newly created nodehGraph- graph to which to add the nodedependencies- dependencies of the nodecopyParams- parameters for the memory copyctx- context on which to run the node
-
ncuGraphMemcpyNodeGetParams
public static int ncuGraphMemcpyNodeGetParams(long hNode, long nodeParams) Unsafe version of:GraphMemcpyNodeGetParams -
cuGraphMemcpyNodeGetParams
Returns a memcpy node's parameters.Returns the parameters of memcpy node
hNodeinnodeParams.- Parameters:
hNode- node to get the parameters fornodeParams- pointer to return the parameters
-
ncuGraphMemcpyNodeSetParams
public static int ncuGraphMemcpyNodeSetParams(long hNode, long nodeParams) Unsafe version of:GraphMemcpyNodeSetParams -
cuGraphMemcpyNodeSetParams
Sets a memcpy node's parameters.Sets the parameters of memcpy node
hNodetonodeParams.- Parameters:
hNode- node to set the parameters fornodeParams- parameters to copy
-
ncuGraphAddMemsetNode
public static int ncuGraphAddMemsetNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long memsetParams, long ctx) Unsafe version of:GraphAddMemsetNode- Parameters:
numDependencies- number of dependencies
-
cuGraphAddMemsetNode
public static int cuGraphAddMemsetNode(PointerBuffer phGraphNode, long hGraph, @Nullable PointerBuffer dependencies, CUDA_MEMSET_NODE_PARAMS memsetParams, long ctx) Creates a memset node and adds it to a graph.Creates a new memset node and adds it to
hGraphwithnumDependenciesdependencies specified viadependencies. It is possible fornumDependenciesto be 0, in which case the node will be placed at the root of the graph.dependenciesmay not have any duplicate entries. A handle to the new node will be returned inphGraphNode.The element size must be 1, 2, or 4 bytes. When the graph is launched, the node will perform the memset described by
memsetParams.- Parameters:
phGraphNode- returns newly created nodehGraph- graph to which to add the nodedependencies- dependencies of the nodememsetParams- parameters for the memory setctx- context on which to run the node
-
ncuGraphMemsetNodeGetParams
public static int ncuGraphMemsetNodeGetParams(long hNode, long nodeParams) Unsafe version of:GraphMemsetNodeGetParams -
cuGraphMemsetNodeGetParams
Returns a memset node's parameters.Returns the parameters of memset node
hNodeinnodeParams.- Parameters:
hNode- node to get the parameters fornodeParams- pointer to return the parameters
-
ncuGraphMemsetNodeSetParams
public static int ncuGraphMemsetNodeSetParams(long hNode, long nodeParams) Unsafe version of:GraphMemsetNodeSetParams -
cuGraphMemsetNodeSetParams
Sets a memset node's parameters.Sets the parameters of memset node
hNodetonodeParams.- Parameters:
hNode- node to set the parameters fornodeParams- parameters to copy
-
ncuGraphAddHostNode
public static int ncuGraphAddHostNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long nodeParams) Unsafe version of:GraphAddHostNode- Parameters:
numDependencies- number of dependencies
-
cuGraphAddHostNode
public static int cuGraphAddHostNode(PointerBuffer phGraphNode, long hGraph, @Nullable PointerBuffer dependencies, CUDA_HOST_NODE_PARAMS nodeParams) Creates a host execution node and adds it to a graph.Creates a new CPU execution node and adds it to
hGraphwithnumDependenciesdependencies specified viadependenciesand arguments specified innodeParams. It is possible fornumDependenciesto be 0, in which case the node will be placed at the root of the graph.dependenciesmay not have any duplicate entries. A handle to the new node will be returned inphGraphNode.When the graph is launched, the node will invoke the specified CPU function. Host nodes are not supported under MPS with pre-Volta GPUs.
- Parameters:
phGraphNode- returns newly created nodehGraph- graph to which to add the nodedependencies- dependencies of the nodenodeParams- parameters for the host node
-
ncuGraphHostNodeGetParams
public static int ncuGraphHostNodeGetParams(long hNode, long nodeParams) Unsafe version of:GraphHostNodeGetParams -
cuGraphHostNodeGetParams
Returns a host node's parameters.Returns the parameters of host node
hNodeinnodeParams.- Parameters:
hNode- node to get the parameters fornodeParams- pointer to return the parameters
-
ncuGraphHostNodeSetParams
public static int ncuGraphHostNodeSetParams(long hNode, long nodeParams) Unsafe version of:GraphHostNodeSetParams -
cuGraphHostNodeSetParams
Sets a host node's parameters.Sets the parameters of host node
hNodetonodeParams.- Parameters:
hNode- node to set the parameters fornodeParams- parameters to copy
-
ncuGraphAddChildGraphNode
public static int ncuGraphAddChildGraphNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long childGraph) Unsafe version of:GraphAddChildGraphNode- Parameters:
numDependencies- number of dependencies
-
cuGraphAddChildGraphNode
public static int cuGraphAddChildGraphNode(PointerBuffer phGraphNode, long hGraph, @Nullable PointerBuffer dependencies, long childGraph) Creates a child graph node and adds it to a graph.Creates a new node which executes an embedded graph, and adds it to
hGraphwithnumDependenciesdependencies specified viadependencies. It is possible fornumDependenciesto be 0, in which case the node will be placed at the root of the graph.dependenciesmay not have any duplicate entries. A handle to the new node will be returned inphGraphNode.If
hGraphcontains allocation or free nodes, this call will return an error.The node executes an embedded child graph. The child graph is cloned in this call.
- Parameters:
phGraphNode- returns newly created nodehGraph- graph to which to add the nodedependencies- dependencies of the nodechildGraph- the graph to clone into this node
-
ncuGraphChildGraphNodeGetGraph
public static int ncuGraphChildGraphNodeGetGraph(long hNode, long phGraph) Unsafe version of:GraphChildGraphNodeGetGraph -
cuGraphChildGraphNodeGetGraph
Gets a handle to the embedded graph of a child graph node.Gets a handle to the embedded graph in a child graph node. This call does not clone the graph. Changes to the graph will be reflected in the node, and the node retains ownership of the graph.
Allocation and free nodes cannot be added to the returned graph. Attempting to do so will return an error.
- Parameters:
hNode- node to get the embedded graph forphGraph- location to store a handle to the graph
-
ncuGraphAddEmptyNode
public static int ncuGraphAddEmptyNode(long phGraphNode, long hGraph, long dependencies, long numDependencies) Unsafe version of:GraphAddEmptyNode- Parameters:
numDependencies- number of dependencies
-
cuGraphAddEmptyNode
public static int cuGraphAddEmptyNode(PointerBuffer phGraphNode, long hGraph, @Nullable PointerBuffer dependencies) Creates an empty node and adds it to a graph.Creates a new node which performs no operation, and adds it to
hGraphwithnumDependenciesdependencies specified viadependencies. It is possible fornumDependenciesto be 0, in which case the node will be placed at the root of the graph.dependenciesmay not have any duplicate entries. A handle to the new node will be returned inphGraphNode.An empty node performs no operation during execution, but can be used for transitive ordering. For example, a phased execution graph with 2 groups of n nodes with a barrier between them can be represented using an empty node and 2*n dependency edges, rather than no empty node and n^2 dependency edges.
- Parameters:
phGraphNode- returns newly created nodehGraph- graph to which to add the nodedependencies- dependencies of the node
-
ncuGraphAddEventRecordNode
public static int ncuGraphAddEventRecordNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long event) Unsafe version of:GraphAddEventRecordNode- Parameters:
numDependencies- number of dependencies
-
cuGraphAddEventRecordNode
public static int cuGraphAddEventRecordNode(PointerBuffer phGraphNode, long hGraph, @Nullable PointerBuffer dependencies, long event) Creates an event record node and adds it to a graph.Creates a new event record node and adds it to
hGraphwithnumDependenciesdependencies specified viadependenciesand event specified inevent. It is possible fornumDependenciesto be 0, in which case the node will be placed at the root of the graph.dependenciesmay not have any duplicate entries. A handle to the new node will be returned inphGraphNode.Each launch of the graph will record
eventto capture execution of the node's dependencies.- Parameters:
phGraphNode- returns newly created nodehGraph- graph to which to add the nodedependencies- dependencies of the nodeevent- event for the node
-
ncuGraphEventRecordNodeGetEvent
public static int ncuGraphEventRecordNodeGetEvent(long hNode, long event_out) Unsafe version of:GraphEventRecordNodeGetEvent -
cuGraphEventRecordNodeGetEvent
Returns the event associated with an event record node.Returns the event of event record node
hNodeinevent_out.- Parameters:
hNode- node to get the event forevent_out- pointer to return the event
-
cuGraphEventRecordNodeSetEvent
public static int cuGraphEventRecordNodeSetEvent(long hNode, long event) Sets an event record node's event.Sets the event of event record node
hNodetoevent.- Parameters:
hNode- node to set the event forevent- event to use
-
ncuGraphAddEventWaitNode
public static int ncuGraphAddEventWaitNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long event) Unsafe version of:GraphAddEventWaitNode- Parameters:
numDependencies- number of dependencies
-
cuGraphAddEventWaitNode
public static int cuGraphAddEventWaitNode(PointerBuffer phGraphNode, long hGraph, @Nullable PointerBuffer dependencies, long event) Creates an event wait node and adds it to a graph.Creates a new event wait node and adds it to
hGraphwithnumDependenciesdependencies specified viadependenciesand event specified inevent. It is possible fornumDependenciesto be 0, in which case the node will be placed at the root of the graph.dependenciesmay not have any duplicate entries. A handle to the new node will be returned inphGraphNode.The graph node will wait for all work captured in
event. SeeEventRecordfor details on what is captured by an event.eventmay be from a different context or device than the launch stream.- Parameters:
phGraphNode- returns newly created nodehGraph- graph to which to add the nodedependencies- dependencies of the nodeevent- event for the node
-
ncuGraphEventWaitNodeGetEvent
public static int ncuGraphEventWaitNodeGetEvent(long hNode, long event_out) Unsafe version of:GraphEventWaitNodeGetEvent -
cuGraphEventWaitNodeGetEvent
Returns the event associated with an event wait node.Returns the event of event wait node
hNodeinevent_out.- Parameters:
hNode- node to get the event forevent_out- pointer to return the event
-
cuGraphEventWaitNodeSetEvent
public static int cuGraphEventWaitNodeSetEvent(long hNode, long event) Sets an event wait node's event.Sets the event of event wait node
hNodetoevent.- Parameters:
hNode- node to set the event forevent- event to use
-
ncuGraphAddExternalSemaphoresSignalNode
public static int ncuGraphAddExternalSemaphoresSignalNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long nodeParams) Unsafe version of:GraphAddExternalSemaphoresSignalNode- Parameters:
numDependencies- number of dependencies
-
cuGraphAddExternalSemaphoresSignalNode
public static int cuGraphAddExternalSemaphoresSignalNode(PointerBuffer phGraphNode, long hGraph, @Nullable PointerBuffer dependencies, CUDA_EXT_SEM_SIGNAL_NODE_PARAMS nodeParams) Creates an external semaphore signal node and adds it to a graph.Creates a new external semaphore signal node and adds it to
hGraphwithnumDependenciesdependencies specified viadependenciesand arguments specified innodeParams. It is possible fornumDependenciesto be 0, in which case the node will be placed at the root of the graph.dependenciesmay not have any duplicate entries. A handle to the new node will be returned inphGraphNode.Performs a signal operation on a set of externally allocated semaphore objects when the node is launched. The operation(s) will occur after all of the node's dependencies have completed.
- Parameters:
phGraphNode- returns newly created nodehGraph- graph to which to add the nodedependencies- dependencies of the nodenodeParams- parameters for the node
-
ncuGraphExternalSemaphoresSignalNodeGetParams
public static int ncuGraphExternalSemaphoresSignalNodeGetParams(long hNode, long params_out) Unsafe version of:GraphExternalSemaphoresSignalNodeGetParams -
cuGraphExternalSemaphoresSignalNodeGetParams
public static int cuGraphExternalSemaphoresSignalNodeGetParams(long hNode, CUDA_EXT_SEM_SIGNAL_NODE_PARAMS params_out) Returns an external semaphore signal node's parameters.Returns the parameters of an external semaphore signal node
hNodeinparams_out. TheextSemArrayandparamsArrayreturned inparams_out, are owned by the node. This memory remains valid until the node is destroyed or its parameters are modified, and should not be modified directly. UseGraphExternalSemaphoresSignalNodeSetParamsto update the parameters of this node.- Parameters:
hNode- node to get the parameters forparams_out- pointer to return the parameters
-
ncuGraphExternalSemaphoresSignalNodeSetParams
public static int ncuGraphExternalSemaphoresSignalNodeSetParams(long hNode, long nodeParams) Unsafe version of:GraphExternalSemaphoresSignalNodeSetParams -
cuGraphExternalSemaphoresSignalNodeSetParams
public static int cuGraphExternalSemaphoresSignalNodeSetParams(long hNode, CUDA_EXT_SEM_SIGNAL_NODE_PARAMS nodeParams) Sets an external semaphore signal node's parameters.Sets the parameters of an external semaphore signal node
hNodetonodeParams.- Parameters:
hNode- node to set the parameters fornodeParams- parameters to copy
-
ncuGraphAddExternalSemaphoresWaitNode
public static int ncuGraphAddExternalSemaphoresWaitNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long nodeParams) Unsafe version of:GraphAddExternalSemaphoresWaitNode- Parameters:
numDependencies- number of dependencies
-
cuGraphAddExternalSemaphoresWaitNode
public static int cuGraphAddExternalSemaphoresWaitNode(PointerBuffer phGraphNode, long hGraph, @Nullable PointerBuffer dependencies, CUDA_EXT_SEM_WAIT_NODE_PARAMS nodeParams) Creates an external semaphore wait node and adds it to a graph.Creates a new external semaphore wait node and adds it to
hGraphwithnumDependenciesdependencies specified viadependenciesand arguments specified innodeParams. It is possible fornumDependenciesto be 0, in which case the node will be placed at the root of the graph.dependenciesmay not have any duplicate entries. A handle to the new node will be returned inphGraphNode.Performs a wait operation on a set of externally allocated semaphore objects when the node is launched. The node's dependencies will not be launched until the wait operation has completed.
- Parameters:
phGraphNode- returns newly created nodehGraph- graph to which to add the nodedependencies- dependencies of the nodenodeParams- parameters for the node
-
ncuGraphExternalSemaphoresWaitNodeGetParams
public static int ncuGraphExternalSemaphoresWaitNodeGetParams(long hNode, long params_out) Unsafe version of:GraphExternalSemaphoresWaitNodeGetParams -
cuGraphExternalSemaphoresWaitNodeGetParams
public static int cuGraphExternalSemaphoresWaitNodeGetParams(long hNode, CUDA_EXT_SEM_WAIT_NODE_PARAMS params_out) Returns an external semaphore wait node's parameters.Returns the parameters of an external semaphore wait node
hNodeinparams_out. TheextSemArrayandparamsArrayreturned inparams_out, are owned by the node. This memory remains valid until the node is destroyed or its parameters are modified, and should not be modified directly. UseGraphExternalSemaphoresSignalNodeSetParamsto update the parameters of this node.- Parameters:
hNode- node to get the parameters forparams_out- pointer to return the parameters
-
ncuGraphExternalSemaphoresWaitNodeSetParams
public static int ncuGraphExternalSemaphoresWaitNodeSetParams(long hNode, long nodeParams) Unsafe version of:GraphExternalSemaphoresWaitNodeSetParams -
cuGraphExternalSemaphoresWaitNodeSetParams
public static int cuGraphExternalSemaphoresWaitNodeSetParams(long hNode, CUDA_EXT_SEM_WAIT_NODE_PARAMS nodeParams) Sets an external semaphore wait node's parameters.Sets the parameters of an external semaphore wait node
hNodetonodeParams.- Parameters:
hNode- node to set the parameters fornodeParams- parameters to copy
-
ncuGraphAddMemAllocNode
public static int ncuGraphAddMemAllocNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long nodeParams) Unsafe version of:GraphAddMemAllocNode- Parameters:
numDependencies- number of dependencies
-
cuGraphAddMemAllocNode
public static int cuGraphAddMemAllocNode(PointerBuffer phGraphNode, long hGraph, @Nullable PointerBuffer dependencies, CUDA_MEM_ALLOC_NODE_PARAMS nodeParams) Creates an allocation node and adds it to a graph.Creates a new allocation node and adds it to
hGraphwithnumDependenciesdependencies specified viadependenciesand arguments specified innodeParams. It is possible fornumDependenciesto be 0, in which case the node will be placed at the root of the graph.dependenciesmay not have any duplicate entries. A handle to the new node will be returned inphGraphNode.When
GraphAddMemAllocNodecreates an allocation node, it returns the address of the allocation innodeParams.dptr. The allocation's address remains fixed across instantiations and launches.If the allocation is freed in the same graph, by creating a free node using
GraphAddMemFreeNode, the allocation can be accessed by nodes ordered after the allocation node but before the free node. These allocations cannot be freed outside the owning graph, and they can only be freed once in the owning graph.If the allocation is not freed in the same graph, then it can be accessed not only by nodes in the graph which are ordered after the allocation node, but also by stream operations ordered after the graph's execution but before the allocation is freed.
Allocations which are not freed in the same graph can be freed by:
- passing the allocation to
MemFreeAsyncorMemFree; - launching a graph with a free node for that allocation; or
- specifying
CUDA_GRAPH_INSTANTIATE_FLAG_AUTO_FREE_ON_LAUNCHduring instantiation, which makes each launch behave as though it calledMemFreeAsyncfor every unfreed allocation.
It is not possible to free an allocation in both the owning graph and another graph. If the allocation is freed in the same graph, a free node cannot be added to another graph. If the allocation is freed in another graph, a free node can no longer be added to the owning graph.
The following restrictions apply to graphs which contain allocation and/or memory free nodes:
- Nodes and edges of the graph cannot be deleted.
- The graph cannot be used in a child node.
- Only one instantiation of the graph may exist at any point in time.
- The graph cannot be cloned.
- Parameters:
phGraphNode- returns newly created nodehGraph- graph to which to add the nodedependencies- dependencies of the nodenodeParams- parameters for the node
- passing the allocation to
-
ncuGraphMemAllocNodeGetParams
public static int ncuGraphMemAllocNodeGetParams(long hNode, long params_out) Unsafe version of:GraphMemAllocNodeGetParams -
cuGraphMemAllocNodeGetParams
Returns a memory alloc node's parameters.Returns the parameters of a memory alloc node
hNodeinparams_out. ThepoolPropsandaccessDescsreturned inparams_out, are owned by the node. This memory remains valid until the node is destroyed. The returned parameters must not be modified.- Parameters:
hNode- node to get the parameters forparams_out- pointer to return the parameters
-
ncuGraphAddMemFreeNode
public static int ncuGraphAddMemFreeNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long dptr) Unsafe version of:GraphAddMemFreeNode- Parameters:
numDependencies- number of dependencies
-
cuGraphAddMemFreeNode
public static int cuGraphAddMemFreeNode(PointerBuffer phGraphNode, long hGraph, @Nullable PointerBuffer dependencies, long dptr) Creates a memory free node and adds it to a graph.Creates a new memory free node and adds it to
hGraphwithnumDependenciesdependencies specified viadependenciesand arguments specified innodeParams. It is possible fornumDependenciesto be 0, in which case the node will be placed at the root of the graph.dependenciesmay not have any duplicate entries. A handle to the new node will be returned inphGraphNode.GraphAddMemFreeNodewill returnCUDA_ERROR_INVALID_VALUEif the user attempts to free:- an allocation twice in the same graph.
- an address that was not returned by an allocation node.
- an invalid address.
The following restrictions apply to graphs which contain allocation and/or memory free nodes:
- Nodes and edges of the graph cannot be deleted.
- The graph cannot be used in a child node.
- Only one instantiation of the graph may exist at any point in time.
- The graph cannot be cloned.
- Parameters:
phGraphNode- returns newly created nodehGraph- graph to which to add the nodedependencies- dependencies of the nodedptr- address of memory to free
-
ncuGraphMemFreeNodeGetParams
public static int ncuGraphMemFreeNodeGetParams(long hNode, long dptr_out) Unsafe version of:GraphMemFreeNodeGetParams -
cuGraphMemFreeNodeGetParams
Returns a memory free node's parameters.Returns the address of a memory free node
hNodeindptr_out.- Parameters:
hNode- node to get the parameters fordptr_out- pointer to return the device address
-
cuDeviceGraphMemTrim
public static int cuDeviceGraphMemTrim(int device) Free unused memory that was cached on the specified device for use with graphs back to the OS.Blocks which are not in use by a graph that is either currently executing or scheduled to execute are freed back to the operating system.
- Parameters:
device- the device for which cached memory should be freed
-
ncuDeviceGetGraphMemAttribute
public static int ncuDeviceGetGraphMemAttribute(int device, int attr, long value) Unsafe version of:DeviceGetGraphMemAttribute -
cuDeviceGetGraphMemAttribute
Query asynchronous allocation attributes related to graphs.Valid attributes are:
GRAPH_MEM_ATTR_USED_MEM_CURRENT: Amount of memory, in bytes, currently associated with graphsGRAPH_MEM_ATTR_USED_MEM_HIGH: High watermark of memory, in bytes, associated with graphs since the last time it was reset. High watermark can only be reset to zero.GRAPH_MEM_ATTR_RESERVED_MEM_CURRENT: Amount of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator.GRAPH_MEM_ATTR_RESERVED_MEM_HIGH: High watermark of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator.
- Parameters:
device- specifies the scope of the queryattr- attribute to getvalue- retrieved value
-
cuDeviceGetGraphMemAttribute
Query asynchronous allocation attributes related to graphs.Valid attributes are:
GRAPH_MEM_ATTR_USED_MEM_CURRENT: Amount of memory, in bytes, currently associated with graphsGRAPH_MEM_ATTR_USED_MEM_HIGH: High watermark of memory, in bytes, associated with graphs since the last time it was reset. High watermark can only be reset to zero.GRAPH_MEM_ATTR_RESERVED_MEM_CURRENT: Amount of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator.GRAPH_MEM_ATTR_RESERVED_MEM_HIGH: High watermark of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator.
- Parameters:
device- specifies the scope of the queryattr- attribute to getvalue- retrieved value
-
ncuDeviceSetGraphMemAttribute
public static int ncuDeviceSetGraphMemAttribute(int device, int attr, long value) Unsafe version of:DeviceSetGraphMemAttribute -
cuDeviceSetGraphMemAttribute
Set asynchronous allocation attributes related to graphs.Valid attributes are:
GRAPH_MEM_ATTR_USED_MEM_HIGH: High watermark of memory, in bytes, associated with graphs since the last time it was reset. High watermark can only be reset to zero.GRAPH_MEM_ATTR_RESERVED_MEM_HIGH: High watermark of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator.
- Parameters:
device- specifies the scope of the queryattr- attribute to getvalue- pointer to value to set
-
cuDeviceSetGraphMemAttribute
Set asynchronous allocation attributes related to graphs.Valid attributes are:
GRAPH_MEM_ATTR_USED_MEM_HIGH: High watermark of memory, in bytes, associated with graphs since the last time it was reset. High watermark can only be reset to zero.GRAPH_MEM_ATTR_RESERVED_MEM_HIGH: High watermark of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator.
- Parameters:
device- specifies the scope of the queryattr- attribute to getvalue- pointer to value to set
-
ncuGraphClone
public static int ncuGraphClone(long phGraphClone, long originalGraph) Unsafe version of:GraphClone -
cuGraphClone
Clones a graph.This function creates a copy of
originalGraphand returns it inphGraphClone. All parameters are copied into the cloned graph. The original graph may be modified after this call without affecting the clone.Child graph nodes in the original graph are recursively copied into the clone.
- Parameters:
phGraphClone- returns newly created cloned graphoriginalGraph- graph to clone
-
ncuGraphNodeFindInClone
public static int ncuGraphNodeFindInClone(long phNode, long hOriginalNode, long hClonedGraph) Unsafe version of:GraphNodeFindInClone -
cuGraphNodeFindInClone
public static int cuGraphNodeFindInClone(PointerBuffer phNode, long hOriginalNode, long hClonedGraph) Finds a cloned version of a node.This function returns the node in
hClonedGraphcorresponding tohOriginalNodein the original graph.hClonedGraphmust have been cloned fromhOriginalGraphviaGraphClone.hOriginalNodemust have been inhOriginalGraphat the time of the call toGraphClone, and the corresponding cloned node inhClonedGraphmust not have been removed. The cloned node is then returned viaphClonedNode.- Parameters:
phNode- returns handle to the cloned nodehOriginalNode- handle to the original nodehClonedGraph- cloned graph to query
-
ncuGraphNodeGetType
public static int ncuGraphNodeGetType(long hNode, long type) Unsafe version of:GraphNodeGetType -
cuGraphNodeGetType
Returns a node's type.Returns the node type of
hNodeintype.- Parameters:
hNode- node to querytype- pointer to return the node type
-
ncuGraphGetNodes
public static int ncuGraphGetNodes(long hGraph, long nodes, long numNodes) Unsafe version of:GraphGetNodes- Parameters:
numNodes- see description
-
cuGraphGetNodes
public static int cuGraphGetNodes(long hGraph, @Nullable PointerBuffer nodes, PointerBuffer numNodes) Returns a graph's nodes.Returns a list of
hGraph'snodes.nodesmay beNULL, in which case this function will return the number of nodes innumNodes. Otherwise,numNodesentries will be filled in. IfnumNodesis higher than the actual number of nodes, the remaining entries innodeswill be set toNULL, and the number of nodes actually obtained will be returned innumNodes.- Parameters:
hGraph- graph to querynodes- pointer to return the nodesnumNodes- see description
-
ncuGraphGetRootNodes
public static int ncuGraphGetRootNodes(long hGraph, long rootNodes, long numRootNodes) Unsafe version of:GraphGetRootNodes- Parameters:
numRootNodes- see description
-
cuGraphGetRootNodes
public static int cuGraphGetRootNodes(long hGraph, @Nullable PointerBuffer rootNodes, PointerBuffer numRootNodes) Returns a graph's root nodes.Returns a list of
hGraph'sroot nodes.rootNodesmay beNULL, in which case this function will return the number of root nodes innumRootNodes. Otherwise,numRootNodesentries will be filled in. IfnumRootNodesis higher than the actual number of root nodes, the remaining entries inrootNodeswill be set toNULL, and the number of nodes actually obtained will be returned innumRootNodes.- Parameters:
hGraph- graph to queryrootNodes- pointer to return the root nodesnumRootNodes- see description
-
ncuGraphGetEdges
public static int ncuGraphGetEdges(long hGraph, long from, long to, long numEdges) Unsafe version of:GraphGetEdges- Parameters:
numEdges- see description
-
cuGraphGetEdges
public static int cuGraphGetEdges(long hGraph, @Nullable PointerBuffer from, @Nullable PointerBuffer to, PointerBuffer numEdges) Returns a graph's dependency edges.Returns a list of
hGraph'sdependency edges. Edges are returned via corresponding indices infromandto;that is, the node into[i]has a dependency on the node infrom[i].fromandtomay both beNULL, in which case this function only returns the number of edges innumEdges. Otherwise,numEdgesentries will be filled in. IfnumEdgesis higher than the actual number of edges, the remaining entries infromandtowill be set toNULL, and the number of edges actually returned will be written tonumEdges.- Parameters:
hGraph- graph to get the edges fromfrom- location to return edge endpointsto- location to return edge endpointsnumEdges- see description
-
ncuGraphNodeGetDependencies
public static int ncuGraphNodeGetDependencies(long hNode, long dependencies, long numDependencies) Unsafe version of:GraphNodeGetDependencies- Parameters:
numDependencies- see description
-
cuGraphNodeGetDependencies
public static int cuGraphNodeGetDependencies(long hNode, @Nullable PointerBuffer dependencies, PointerBuffer numDependencies) Returns a node's dependencies.Returns a list of
node'sdependencies.dependenciesmay beNULL, in which case this function will return the number of dependencies innumDependencies. Otherwise,numDependenciesentries will be filled in. IfnumDependenciesis higher than the actual number of dependencies, the remaining entries independencieswill be set toNULL, and the number of nodes actually obtained will be returned innumDependencies.- Parameters:
hNode- node to querydependencies- pointer to return the dependenciesnumDependencies- see description
-
ncuGraphNodeGetDependentNodes
public static int ncuGraphNodeGetDependentNodes(long hNode, long dependentNodes, long numDependentNodes) Unsafe version of:GraphNodeGetDependentNodes- Parameters:
numDependentNodes- see description
-
cuGraphNodeGetDependentNodes
public static int cuGraphNodeGetDependentNodes(long hNode, @Nullable PointerBuffer dependentNodes, PointerBuffer numDependentNodes) Returns a node's dependent nodes.Returns a list of
node'sdependent nodes.dependentNodesmay beNULL, in which case this function will return the number of dependent nodes innumDependentNodes. Otherwise,numDependentNodesentries will be filled in. IfnumDependentNodesis higher than the actual number of dependent nodes, the remaining entries independentNodeswill be set toNULL, and the number of nodes actually obtained will be returned innumDependentNodes.- Parameters:
hNode- node to querydependentNodes- pointer to return the dependent nodesnumDependentNodes- see description
-
ncuGraphAddDependencies
public static int ncuGraphAddDependencies(long hGraph, long from, long to, long numDependencies) Unsafe version of:GraphAddDependencies- Parameters:
numDependencies- number of dependencies to be added
-
cuGraphAddDependencies
public static int cuGraphAddDependencies(long hGraph, @Nullable PointerBuffer from, @Nullable PointerBuffer to) Adds dependency edges to a graph.The number of dependencies to be added is defined by
numDependenciesElements infromandtoat corresponding indices define a dependency. Each node infromandtomust belong tohGraph.If
numDependenciesis 0, elements infromandtowill be ignored. Specifying an existing dependency will return an error.- Parameters:
hGraph- graph to which dependencies are addedfrom- array of nodes that provide the dependenciesto- array of dependent nodes
-
ncuGraphRemoveDependencies
public static int ncuGraphRemoveDependencies(long hGraph, long from, long to, long numDependencies) Unsafe version of:GraphRemoveDependencies- Parameters:
numDependencies- number of dependencies to be removed
-
cuGraphRemoveDependencies
public static int cuGraphRemoveDependencies(long hGraph, @Nullable PointerBuffer from, @Nullable PointerBuffer to) Removes dependency edges from a graph.The number of
dependenciesto be removed is defined bynumDependencies. Elements infromandtoat corresponding indices define a dependency. Each node infromandtomust belong tohGraph.If
numDependenciesis 0, elements infromandtowill be ignored. Specifying a non-existing dependency will return an error.Dependencies cannot be removed from graphs which contain allocation or free nodes. Any attempt to do so will return an error.
- Parameters:
hGraph- graph from which to remove dependenciesfrom- array of nodes that provide the dependenciesto- array of dependent nodes
-
cuGraphDestroyNode
public static int cuGraphDestroyNode(long hNode) Remove a node from the graph.Removes
hNodefrom its graph. This operation also severs any dependencies of other nodes onhNodeand vice versa.Nodes which belong to a graph which contains allocation or free nodes cannot be destroyed. Any attempt to do so will return an error.
- Parameters:
hNode- node to remove
-
ncuGraphInstantiate
public static int ncuGraphInstantiate(long phGraphExec, long hGraph, long phErrorNode, long logBuffer, long bufferSize) Unsafe version of:GraphInstantiate- Parameters:
bufferSize- size of the log buffer in bytes
-
cuGraphInstantiate
public static int cuGraphInstantiate(PointerBuffer phGraphExec, long hGraph, PointerBuffer phErrorNode, ByteBuffer logBuffer) Creates an executable graph from a graph.Instantiates
hGraphas an executable graph. The graph is validated for any structural constraints or intra-node constraints which were not previously validated. If instantiation is successful, a handle to the instantiated graph is returned inphGraphExec.If there are any errors, diagnostic information may be returned in
errorNodeandlogBuffer. This is the primary way to inspect instantiation errors. The output will be null terminated unless the diagnostics overflow the buffer. In this case, they will be truncated, and the last byte can be inspected to determine if truncation occurred.- Parameters:
phGraphExec- returns instantiated graphhGraph- graph to instantiatephErrorNode- in case of an instantiation error, this may be modified to indicate a node contributing to the errorlogBuffer- a character buffer to store diagnostic messages
-
ncuGraphInstantiateWithFlags
public static int ncuGraphInstantiateWithFlags(long phGraphExec, long hGraph, long flags) Unsafe version of:GraphInstantiateWithFlags -
cuGraphInstantiateWithFlags
Creates an executable graph from a graph.Instantiates
hGraphas an executable graph. The graph is validated for any structural constraints or intra-node constraints which were not previously validated. If instantiation is successful, a handle to the instantiated graph is returned inphGraphExec.The
flagsparameter controls the behavior of instantiation and subsequent graph launches. Valid flags are:CUDA_GRAPH_INSTANTIATE_FLAG_AUTO_FREE_ON_LAUNCH, which configures a graph containing memory allocation nodes to automatically free any unfreed memory allocations before the graph is relaunched.
If
hGraphcontains any allocation or free nodes, there can be at most one executable graph in existence for that graph at a time.An attempt to instantiate a second executable graph before destroying the first with
GraphExecDestroywill result in an error.- Parameters:
phGraphExec- returns instantiated graphhGraph- graph to instantiateflags- flags to control instantiation. SeeCUgraphInstantiate_flags.
-
ncuGraphExecKernelNodeSetParams
public static int ncuGraphExecKernelNodeSetParams(long hGraphExec, long hNode, long nodeParams) Unsafe version of:GraphExecKernelNodeSetParams -
cuGraphExecKernelNodeSetParams
public static int cuGraphExecKernelNodeSetParams(long hGraphExec, long hNode, CUDA_KERNEL_NODE_PARAMS nodeParams) Sets the parameters for a kernel node in the givengraphExec.Sets the parameters of a kernel node in an executable graph
hGraphExec. The node is identified by the corresponding nodehNodein the non-executable graph, from which the executable graph was instantiated.hNodemust not have been removed from the original graph. Thefuncfield ofnodeParamscannot be modified and must match the original value. All other values can be modified.The modifications take effect at the next launch of
hGraphExec. Already enqueued or running launches ofhGraphExecare not affected by this call.hNodeis also not modified by this call.- Parameters:
hGraphExec- the executable graph in which to set the specified nodehNode- kernel node from the graph from which graphExec was instantiatednodeParams- updated parameters to set
-
ncuGraphExecMemcpyNodeSetParams
public static int ncuGraphExecMemcpyNodeSetParams(long hGraphExec, long hNode, long copyParams, long ctx) Unsafe version of:GraphExecMemcpyNodeSetParams -
cuGraphExecMemcpyNodeSetParams
public static int cuGraphExecMemcpyNodeSetParams(long hGraphExec, long hNode, CUDA_MEMCPY3D copyParams, long ctx) Sets the parameters for a memcpy node in the givengraphExec.Updates the work represented by
hNodeinhGraphExecas thoughhNodehad containedcopyParamsat instantiation.hNodemust remain in the graph which was used to instantiatehGraphExec. Changed edges to and fromhNodeare ignored.The source and destination memory in
copyParamsmust be allocated from the same contexts as the original source and destination memory. Both the instantiation-time memory operands and the memory operands incopyParamsmust be 1-dimensional. Zero-length operations are not supported.The modifications only affect future launches of
hGraphExec. Already enqueued or running launches ofhGraphExecare not affected by this call. hNode is also not modified by this call.Returns
CUDA_ERROR_INVALID_VALUEif the memory operands' mappings changed or either the original or new memory operands are multidimensional.- Parameters:
hGraphExec- the executable graph in which to set the specified nodehNode- memcpy node from the graph which was used to instantiate graphExeccopyParams- the updated parameters to setctx- context on which to run the node
-
ncuGraphExecMemsetNodeSetParams
public static int ncuGraphExecMemsetNodeSetParams(long hGraphExec, long hNode, long memsetParams, long ctx) Unsafe version of:GraphExecMemsetNodeSetParams -
cuGraphExecMemsetNodeSetParams
public static int cuGraphExecMemsetNodeSetParams(long hGraphExec, long hNode, CUDA_MEMSET_NODE_PARAMS memsetParams, long ctx) Sets the parameters for amemsetnode in the givengraphExec.Updates the work represented by
hNodeinhGraphExecas thoughhNodehad containedmemsetParamsat instantiation.hNodemust remain in the graph which was used to instantiatehGraphExec. Changed edges to and fromhNodeare ignored.The destination memory in
memsetParamsmust be allocated from the same contexts as the original destination memory. Both the instantiation-time memory operand and the memory operand inmemsetParamsmust be 1-dimensional. Zero-length operations are not supported.The modifications only affect future launches of
hGraphExec. Already enqueued or running launches ofhGraphExecare not affected by this call. hNode is also not modified by this call.Returns CUDA_ERROR_INVALID_VALUE if the memory operand's mappings changed or either the original or new memory operand are multidimensional.
- Parameters:
hGraphExec- the executable graph in which to set the specified nodehNode- memset node from the graph which was used to instantiate graphExecmemsetParams- the updated parameters to setctx- context on which to run the node
-
ncuGraphExecHostNodeSetParams
public static int ncuGraphExecHostNodeSetParams(long hGraphExec, long hNode, long nodeParams) Unsafe version of:GraphExecHostNodeSetParams -
cuGraphExecHostNodeSetParams
public static int cuGraphExecHostNodeSetParams(long hGraphExec, long hNode, CUDA_HOST_NODE_PARAMS nodeParams) Sets the parameters for a host node in the givengraphExec.Updates the work represented by
hNodeinhGraphExecas thoughhNodehad containednodeParamsat instantiation.hNodemust remain in the graph which was used to instantiatehGraphExec. Changed edges to and fromhNodeare ignored.The modifications only affect future launches of
hGraphExec. Already enqueued or running launches ofhGraphExecare not affected by this call. hNode is also not modified by this call.- Parameters:
hGraphExec- the executable graph in which to set the specified nodehNode- host node from the graph which was used to instantiate graphExecnodeParams- the updated parameters to set
-
cuGraphExecChildGraphNodeSetParams
public static int cuGraphExecChildGraphNodeSetParams(long hGraphExec, long hNode, long childGraph) Updates node parameters in the child graph node in the givengraphExec.Updates the work represented by
hNodeinhGraphExecas though the nodes contained inhNode'sgraph had the parameters contained inchildGraph'snodes at instantiation.hNodemust remain in the graph which was used to instantiatehGraphExec. Changed edges to and fromhNodeare ignored.The modifications only affect future launches of
hGraphExec. Already enqueued or running launches ofhGraphExecare not affected by this call.hNodeis also not modified by this call.The topology of
childGraph, as well as the node insertion order, must match that of the graph contained inhNode. SeeGraphExecUpdatefor a list of restrictions on what can be updated in an instantiated graph. The update is recursive, so child graph nodes contained within the top level child graph will also be updated.- Parameters:
hGraphExec- the executable graph in which to set the specified nodehNode- host node from the graph which was used to instantiategraphExecchildGraph- the graph supplying the updated parameters
-
cuGraphExecEventRecordNodeSetEvent
public static int cuGraphExecEventRecordNodeSetEvent(long hGraphExec, long hNode, long event) Sets the event for an event record node in the givengraphExec.Sets the event of an event record node in an executable graph
hGraphExec. The node is identified by the corresponding nodehNodein the non-executable graph, from which the executable graph was instantiated.The modifications only affect future launches of
hGraphExec. Already enqueued or running launches ofhGraphExecare not affected by this call.hNodeis also not modified by this call.- Parameters:
hGraphExec- the executable graph in which to set the specified nodehNode- event record node from the graph from which graphExec was instantiatedevent- updated event to use
-
cuGraphExecEventWaitNodeSetEvent
public static int cuGraphExecEventWaitNodeSetEvent(long hGraphExec, long hNode, long event) Sets the event for an event wait node in the givengraphExec.Sets the event of an event wait node in an executable graph
hGraphExec. The node is identified by the corresponding nodehNodein the non-executable graph, from which the executable graph was instantiated.The modifications only affect future launches of
hGraphExec. Already enqueued or running launches ofhGraphExecare not affected by this call.hNodeis also not modified by this call.- Parameters:
hGraphExec- the executable graph in which to set the specified nodehNode- event wait node from the graph from which graphExec was instantiatedevent- updated event to use
-
ncuGraphExecExternalSemaphoresSignalNodeSetParams
public static int ncuGraphExecExternalSemaphoresSignalNodeSetParams(long hGraphExec, long hNode, long nodeParams) Unsafe version of:GraphExecExternalSemaphoresSignalNodeSetParams -
cuGraphExecExternalSemaphoresSignalNodeSetParams
public static int cuGraphExecExternalSemaphoresSignalNodeSetParams(long hGraphExec, long hNode, CUDA_EXT_SEM_SIGNAL_NODE_PARAMS nodeParams) Sets the parameters for an external semaphore signal node in the givengraphExec.Sets the parameters of an external semaphore signal node in an executable graph
hGraphExec. The node is identified by the corresponding nodehNodein the non-executable graph, from which the executable graph was instantiated.hNodemust not have been removed from the original graph.The modifications only affect future launches of
hGraphExec. Already enqueued or running launches ofhGraphExecare not affected by this call.hNodeis also not modified by this call.Changing
nodeParams->numExtSemsis not supported.- Parameters:
hGraphExec- the executable graph in which to set the specified nodehNode- semaphore signal node from the graph from which graphExec was instantiatednodeParams- updated Parameters to set
-
ncuGraphExecExternalSemaphoresWaitNodeSetParams
public static int ncuGraphExecExternalSemaphoresWaitNodeSetParams(long hGraphExec, long hNode, long nodeParams) Unsafe version of:GraphExecExternalSemaphoresWaitNodeSetParams -
cuGraphExecExternalSemaphoresWaitNodeSetParams
public static int cuGraphExecExternalSemaphoresWaitNodeSetParams(long hGraphExec, long hNode, CUDA_EXT_SEM_WAIT_NODE_PARAMS nodeParams) Sets the parameters for an external semaphore wait node in the given graphExec.Sets the parameters of an external semaphore wait node in an executable graph
hGraphExec. The node is identified by the corresponding nodehNodein the non-executable graph, from which the executable graph was instantiated.hNodemust not have been removed from the original graph.The modifications only affect future launches of
hGraphExec. Already enqueued or running launches ofhGraphExecare not affected by this call.hNodeis also not modified by this call.Changing
nodeParams->numExtSemsis not supported.- Parameters:
hGraphExec- the executable graph in which to set the specified nodehNode- semaphore wait node from the graph from which graphExec was instantiatednodeParams- updated Parameters to set
-
cuGraphUpload
public static int cuGraphUpload(long hGraphExec, long hStream) Uploads an executable graph in a stream.Uploads
hGraphExecto the device inhStreamwithout executing it. Uploads of the samehGraphExecwill be serialized. Each upload is ordered behind both any previous work inhStreamand any previous launches ofhGraphExec. Uses memory cached bystreamto back the allocations owned byhGraphExec.- Parameters:
hGraphExec- executable graph to uploadhStream- stream in which to upload the graph
-
cuGraphLaunch
public static int cuGraphLaunch(long hGraphExec, long hStream) Launches an executable graph in a stream.Executes
hGraphExecinhStream. Only one instance ofhGraphExecmay be executing at a time. Each launch is ordered behind both any previous work inhStreamand any previous launches ofhGraphExec. To execute a graph concurrently, it must be instantiated multiple times into multiple executable graphs.If any allocations created by
hGraphExecremain unfreed (from a previous launch) andhGraphExecwas not instantiated withCUDA_GRAPH_INSTANTIATE_FLAG_AUTO_FREE_ON_LAUNCH, the launch will fail withCUDA_ERROR_INVALID_VALUE.- Parameters:
hGraphExec- executable graph to launchhStream- stream in which to launch the graph
-
cuGraphExecDestroy
public static int cuGraphExecDestroy(long hGraphExec) Destroys an executable graph.Destroys the executable graph specified by
hGraphExec, as well as all of its executable nodes. If the executable graph is in-flight, it will not be terminated, but rather freed asynchronously on completion.- Parameters:
hGraphExec- executable graph to destroy
-
cuGraphDestroy
public static int cuGraphDestroy(long hGraph) Destroys a graph.Destroys the graph specified by
hGraph, as well as all of its nodes.- Parameters:
hGraph- graph to destroy
-
ncuGraphExecUpdate
public static int ncuGraphExecUpdate(long hGraphExec, long hGraph, long hErrorNode_out, long updateResult_out) Unsafe version of:GraphExecUpdate -
cuGraphExecUpdate
public static int cuGraphExecUpdate(long hGraphExec, long hGraph, PointerBuffer hErrorNode_out, IntBuffer updateResult_out) Check whether an executable graph can be updated with a graph and perform the update if possible.Updates the node parameters in the instantiated graph specified by
hGraphExecwith the node parameters in a topologically identical graph specified byhGraph.Limitations:
- Kernel nodes:
- The owning context of the function cannot change.
- A node whose function originally did not use CUDA dynamic parallelism cannot be updated to a function which uses CDP
- Memset and memcpy nodes:
- The CUDA device(s) to which the operand(s) was allocated/mapped cannot change.
- The source/destination memory must be allocated from the same contexts as the original source/destination memory.
- Only 1D memsets can be changed.
- Additional memcpy node restrictions:
- Changing either the source or destination memory type(i.e. CU_MEMORYTYPE_DEVICE, CU_MEMORYTYPE_ARRAY, etc.) is not supported.
- External semaphore wait nodes and record nodes:
- Changing either the source or destination memory type(i.e. CU_MEMORYTYPE_DEVICE, CU_MEMORYTYPE_ARRAY, etc.) is not supported.
Note: The API may add further restrictions in future releases. The return code should always be checked.
cuGraphExecUpdatesetsupdateResult_outtoGRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGEDunder the following conditions:- The count of nodes directly in
hGraphExecandhGraphdiffer, in which casehErrorNode_outisNULL. - A node is deleted in
hGraphbut not not its pair fromhGraphExec, in which casehErrorNode_outisNULL. - A node is deleted in
hGraphExecbut not its pair fromhGraph, in which casehErrorNode_outis the pairless node fromhGraph. - The dependent nodes of a pair differ, in which case
hErrorNode_outis the node fromhGraph.
cuGraphExecUpdatesetsupdateResult_outto:GRAPH_EXEC_UPDATE_ERRORif passed an invalid value.GRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGEDif the graph topology changedGRAPH_EXEC_UPDATE_ERROR_NODE_TYPE_CHANGEDif the type of a node changed, in which casehErrorNode_outis set to the node fromhGraph.GRAPH_EXEC_UPDATE_ERROR_UNSUPPORTED_FUNCTION_CHANGEif the function changed in an unsupported way(see note above), in which casehErrorNode_outis set to the node fromhGraphGRAPH_EXEC_UPDATE_ERROR_PARAMETERS_CHANGEDif any parameters to a node changed in a way that is not supported, in which casehErrorNode_outis set to the node fromhGraph.GRAPH_EXEC_UPDATE_ERROR_NOT_SUPPORTEDif something about a node is unsupported, like the node's type or configuration, in which casehErrorNode_outis set to the node fromhGraph
If
updateResult_outisn't set in one of the situations described above, the update check passes and cuGraphExecUpdate updateshGraphExecto match the contents ofhGraph. If an error happens during the update,updateResult_outwill be set toGRAPH_EXEC_UPDATE_ERROR; otherwise,updateResult_outis set toGRAPH_EXEC_UPDATE_SUCCESS.cuGraphExecUpdatereturnsCUDA_SUCCESSwhen the updated was performed successfully. It returnsCUDA_ERROR_GRAPH_EXEC_UPDATE_FAILUREif the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.- Parameters:
hGraphExec- the instantiated graph to be updatedhGraph- the graph containing the updated parametershErrorNode_out- the node which caused the permissibility check to forbid the update, if anyupdateResult_out- whether the graph update was permitted. If was forbidden, the reason why.
- Kernel nodes:
-
cuGraphKernelNodeCopyAttributes
public static int cuGraphKernelNodeCopyAttributes(long dst, long src) Copies attributes from source node to destination node.Copies attributes from source node
srcto destination nodedst. Both node must have the same context.- Parameters:
dst- destination nodesrc- source node. For list of attributes seeCUkernelNodeAttrID.
-
ncuGraphKernelNodeGetAttribute
public static int ncuGraphKernelNodeGetAttribute(long hNode, int attr, long value_out) Unsafe version of:GraphKernelNodeGetAttribute -
cuGraphKernelNodeGetAttribute
public static int cuGraphKernelNodeGetAttribute(long hNode, int attr, CUkernelNodeAttrValue value_out) Queries node attribute.Queries attribute
attrfrom nodehNodeand stores it in corresponding member ofvalue_out. -
ncuGraphKernelNodeSetAttribute
public static int ncuGraphKernelNodeSetAttribute(long hNode, int attr, long value) Unsafe version of:GraphKernelNodeSetAttribute -
cuGraphKernelNodeSetAttribute
Sets node attribute.Sets attribute
attron nodehNodefrom corresponding attribute ofvalue. -
ncuGraphDebugDotPrint
public static int ncuGraphDebugDotPrint(long hGraph, long path, int flags) Unsafe version of:GraphDebugDotPrint -
cuGraphDebugDotPrint
Write a DOT file describing graph structure.Using the provided
hGraph, write topatha DOT formatted description of the graph. By default this includes the graph topology, node types, node id, kernel names and memcpy direction.flagscan be specified to write more detailed information about each node type such as parameter values, kernel attributes, node and function handles.- Parameters:
hGraph- the graph to create a DOT file frompath- the path to write the DOT file toflags- flags fromCUgraphDebugDot_flagsfor specifying which additional node information to write
-
cuGraphDebugDotPrint
Write a DOT file describing graph structure.Using the provided
hGraph, write topatha DOT formatted description of the graph. By default this includes the graph topology, node types, node id, kernel names and memcpy direction.flagscan be specified to write more detailed information about each node type such as parameter values, kernel attributes, node and function handles.- Parameters:
hGraph- the graph to create a DOT file frompath- the path to write the DOT file toflags- flags fromCUgraphDebugDot_flagsfor specifying which additional node information to write
-
ncuUserObjectCreate
public static int ncuUserObjectCreate(long object_out, long ptr, long destroy, int initialRefcount, int flags) Unsafe version of:UserObjectCreate -
cuUserObjectCreate
public static int cuUserObjectCreate(PointerBuffer object_out, long ptr, CUhostFnI destroy, int initialRefcount, int flags) Create a user object.Create a user object with the specified destructor callback and initial reference count. The initial references are owned by the caller.
Destructor callbacks cannot make CUDA API calls and should avoid blocking behavior, as they are executed by a shared internal thread. Another thread may be signaled to perform such actions, if it does not block forward progress of tasks scheduled through CUDA.
See CUDA User Objects in the CUDA C++ Programming Guide for more information on user objects.
- Parameters:
object_out- location to return the user object handleptr- the pointer to pass to the destroy functiondestroy- callback to free the user object when it is no longer in useinitialRefcount- the initial refcount to create the object with, typically 1. The initial references are owned by the calling thread.flags- currently it is required to passUSER_OBJECT_NO_DESTRUCTOR_SYNC, which is the only defined flag. This indicates that the destroy callback cannot be waited on by any CUDA API. Users requiring synchronization of the callback should signal its completion manually.
-
cuUserObjectRetain
public static int cuUserObjectRetain(long object, int count) Retain a reference to a user object.Retains new references to a user object. The new references are owned by the caller.
See CUDA User Objects in the CUDA C++ Programming Guide for more information on user objects.
- Parameters:
object- the object to retaincount- the number of references to retain, typically 1. Must be nonzero and not larger than INT_MAX.
-
cuUserObjectRelease
public static int cuUserObjectRelease(long object, int count) Release a reference to a user object.Releases user object references owned by the caller. The object's destructor is invoked if the reference count reaches zero.
It is undefined behavior to release references not owned by the caller, or to use a user object handle after all references are released.
See CUDA User Objects in the CUDA C++ Programming Guide for more information on user objects.
- Parameters:
object- the object to releasecount- the number of references to release, typically 1. Must be nonzero and not larger than INT_MAX.
-
cuGraphRetainUserObject
public static int cuGraphRetainUserObject(long graph, long object, int count, int flags) Retain a reference to a user object from a graph.Creates or moves user object references that will be owned by a CUDA graph.
See CUDA User Objects in the CUDA C++ Programming Guide for more information on user objects.
- Parameters:
graph- the graph to associate the reference withobject- the user object to retain a reference forcount- the number of references to add to the graph, typically 1. Must be nonzero and not larger than INT_MAX.flags- the optional flagGRAPH_USER_OBJECT_MOVEtransfers references from the calling thread, rather than create new references. Pass 0 to create new references.
-
cuGraphReleaseUserObject
public static int cuGraphReleaseUserObject(long graph, long object, int count) Release a user object reference from a graph.Releases user object references owned by a graph.
See CUDA User Objects in the CUDA C++ Programming Guide for more information on user objects.
- Parameters:
graph- the graph that will release the referenceobject- the user object to release a reference forcount- the number of references to release, typically 1. Must be nonzero and not larger than INT_MAX.
-
ncuOccupancyMaxActiveBlocksPerMultiprocessor
public static int ncuOccupancyMaxActiveBlocksPerMultiprocessor(long numBlocks, long func, int blockSize, long dynamicSMemSize) Unsafe version of:OccupancyMaxActiveBlocksPerMultiprocessor -
cuOccupancyMaxActiveBlocksPerMultiprocessor
public static int cuOccupancyMaxActiveBlocksPerMultiprocessor(IntBuffer numBlocks, long func, int blockSize, long dynamicSMemSize) Returns occupancy of a function.Returns in
*numBlocksthe number of the maximum active blocks per streaming multiprocessor.- Parameters:
numBlocks- returned occupancyfunc- kernel for which occupancy is calculatedblockSize- block size the kernel is intended to be launched withdynamicSMemSize- per-block dynamic shared memory usage intended, in bytes
-
ncuOccupancyMaxActiveBlocksPerMultiprocessorWithFlags
public static int ncuOccupancyMaxActiveBlocksPerMultiprocessorWithFlags(long numBlocks, long func, int blockSize, long dynamicSMemSize, int flags) Unsafe version of:OccupancyMaxActiveBlocksPerMultiprocessorWithFlags -
cuOccupancyMaxActiveBlocksPerMultiprocessorWithFlags
public static int cuOccupancyMaxActiveBlocksPerMultiprocessorWithFlags(IntBuffer numBlocks, long func, int blockSize, long dynamicSMemSize, int flags) Returns occupancy of a function.Returns in
*numBlocksthe number of the maximum active blocks per streaming multiprocessor.The
Flagsparameter controls how special cases are handled. The valid flags are:OCCUPANCY_DEFAULT, which maintains the default behavior asOccupancyMaxActiveBlocksPerMultiprocessor;OCCUPANCY_DISABLE_CACHING_OVERRIDE, which suppresses the default behavior on platform where global caching affects occupancy. On such platforms, if caching is enabled, but per-block SM resource usage would result in zero occupancy, the occupancy calculator will calculate the occupancy as if caching is disabled. SettingOCCUPANCY_DISABLE_CACHING_OVERRIDEmakes the occupancy calculator to return 0 in such cases. More information can be found about this feature in the "Unified L1/Texture Cache" section of the Maxwell tuning guide.
- Parameters:
numBlocks- returned occupancyfunc- kernel for which occupancy is calculatedblockSize- block size the kernel is intended to be launched withdynamicSMemSize- per-block dynamic shared memory usage intended, in bytesflags- requested behavior for the occupancy calculator
-
ncuOccupancyMaxPotentialBlockSize
public static int ncuOccupancyMaxPotentialBlockSize(long minGridSize, long blockSize, long func, long blockSizeToDynamicSMemSize, long dynamicSMemSize, int blockSizeLimit) Unsafe version of:OccupancyMaxPotentialBlockSize -
cuOccupancyMaxPotentialBlockSize
public static int cuOccupancyMaxPotentialBlockSize(IntBuffer minGridSize, IntBuffer blockSize, long func, @Nullable CUoccupancyB2DSizeI blockSizeToDynamicSMemSize, long dynamicSMemSize, int blockSizeLimit) Suggest a launch configuration with reasonable occupancy.Returns in
*blockSizea reasonable block size that can achieve the maximum occupancy (or, the maximum number of active warps with the fewest blocks per multiprocessor), and in*minGridSizethe minimum grid size to achieve the maximum occupancy.If
blockSizeLimitis 0, the configurator will use the maximum block size permitted by the device / function instead.If per-block dynamic shared memory allocation is not needed, the user should leave both
blockSizeToDynamicSMemSizeanddynamicSMemSizeas 0.If per-block dynamic shared memory allocation is needed, then if the dynamic shared memory size is constant regardless of block size, the size should be passed through
dynamicSMemSize, andblockSizeToDynamicSMemSizeshould beNULL.Otherwise, if the per-block dynamic shared memory size varies with different block sizes, the user needs to provide a unary function through
blockSizeToDynamicSMemSizethat computes the dynamic shared memory needed byfuncfor any given block size.dynamicSMemSizeis ignored. An example signature is:// Take block size, returns dynamic shared memory needed size_t blockToSmem(int blockSize);- Parameters:
minGridSize- returned minimum grid size needed to achieve the maximum occupancyblockSize- returned maximum block size that can achieve the maximum occupancyfunc- kernel for which launch configuration is calculatedblockSizeToDynamicSMemSize- a function that calculates how much per-block dynamic shared memoryfuncuses based on the block sizedynamicSMemSize- dynamic shared memory usage intended, in bytesblockSizeLimit- the maximum block sizefuncis designed to handle
-
ncuOccupancyMaxPotentialBlockSizeWithFlags
public static int ncuOccupancyMaxPotentialBlockSizeWithFlags(long minGridSize, long blockSize, long func, long blockSizeToDynamicSMemSize, long dynamicSMemSize, int blockSizeLimit, int flags) Unsafe version of:OccupancyMaxPotentialBlockSizeWithFlags -
cuOccupancyMaxPotentialBlockSizeWithFlags
public static int cuOccupancyMaxPotentialBlockSizeWithFlags(IntBuffer minGridSize, IntBuffer blockSize, long func, @Nullable CUoccupancyB2DSizeI blockSizeToDynamicSMemSize, long dynamicSMemSize, int blockSizeLimit, int flags) Suggest a launch configuration with reasonable occupancy.An extended version of
OccupancyMaxPotentialBlockSize. In addition to arguments passed toOccupancyMaxPotentialBlockSize,OccupancyMaxPotentialBlockSizeWithFlagsalso takes aFlagsparameter.The
Flagsparameter controls how special cases are handled. The valid flags are:OCCUPANCY_DEFAULT, which maintains the default behavior asOccupancyMaxPotentialBlockSize;OCCUPANCY_DISABLE_CACHING_OVERRIDE, which suppresses the default behavior on platform where global caching affects occupancy. On such platforms, the launch configurations that produces maximal occupancy might not support global caching. SettingOCCUPANCY_DISABLE_CACHING_OVERRIDEguarantees that the the produced launch configuration is global caching compatible at a potential cost of occupancy. More information can be found about this feature in the "Unified L1/Texture Cache" section of the Maxwell tuning guide.
- Parameters:
minGridSize- returned minimum grid size needed to achieve the maximum occupancyblockSize- returned maximum block size that can achieve the maximum occupancyfunc- kernel for which launch configuration is calculatedblockSizeToDynamicSMemSize- a function that calculates how much per-block dynamic shared memoryfuncuses based on the block sizedynamicSMemSize- dynamic shared memory usage intended, in bytesblockSizeLimit- the maximum block sizefuncis designed to handleflags- options
-
ncuOccupancyAvailableDynamicSMemPerBlock
public static int ncuOccupancyAvailableDynamicSMemPerBlock(long dynamicSmemSize, long func, int numBlocks, int blockSize) Unsafe version of:OccupancyAvailableDynamicSMemPerBlock -
cuOccupancyAvailableDynamicSMemPerBlock
public static int cuOccupancyAvailableDynamicSMemPerBlock(PointerBuffer dynamicSmemSize, long func, int numBlocks, int blockSize) Returns dynamic shared memory available per block when launchingnumBlocksblocks on SM.Returns in
*dynamicSmemSizethe maximum size of dynamic shared memory to allownumBlocksblocks per SM.- Parameters:
dynamicSmemSize- returned maximum dynamic shared memoryfunc- kernel function for which occupancy is calculatednumBlocks- number of blocks to fit on SMblockSize- size of the blocks
-
cuTexRefSetArray
public static int cuTexRefSetArray(long hTexRef, long hArray, int Flags) Binds an array as a texture reference. (Deprecated)Binds the CUDA array
hArrayto the texture referencehTexRef. Any previous address or CUDA array state associated with the texture reference is superseded by this function.Flagsmust be set toTRSA_OVERRIDE_FORMAT. Any CUDA array previously bound tohTexRefis unbound.- Parameters:
hTexRef- texture reference to bindhArray- array to bindFlags- options (must beTRSA_OVERRIDE_FORMAT)
-
cuTexRefSetMipmappedArray
public static int cuTexRefSetMipmappedArray(long hTexRef, long hMipmappedArray, int Flags) Binds a mipmapped array to a texture reference. (Deprecated)Binds the CUDA mipmapped array
hMipmappedArrayto the texture referencehTexRef. Any previous address or CUDA array state associated with the texture reference is superseded by this function.Flagsmust be set toTRSA_OVERRIDE_FORMAT. Any CUDA array previously bound tohTexRefis unbound.- Parameters:
hTexRef- texture reference to bindhMipmappedArray- mipmapped array to bindFlags- options (must beTRSA_OVERRIDE_FORMAT)
-
ncuTexRefSetAddress
public static int ncuTexRefSetAddress(long ByteOffset, long hTexRef, long dptr, long bytes) Unsafe version of:TexRefSetAddress -
cuTexRefSetAddress
Binds an address as a texture reference. (Deprecated)Binds a linear address range to the texture reference
hTexRef. Any previous address or CUDA array state associated with the texture reference is superseded by this function. Any memory previously bound tohTexRefis unbound.Since the hardware enforces an alignment requirement on texture base addresses,
TexRefSetAddresspasses back a byte offset in*ByteOffsetthat must be applied to texture fetches in order to read from the desired memory. This offset must be divided by the texel size and passed to kernels that read from the texture so they can be applied to thetex1Dfetch()function.If the device memory pointer was returned from
MemAlloc, the offset is guaranteed to be 0 andNULLmay be passed as theByteOffsetparameter.The total number of elements (or texels) in the linear address range cannot exceed
DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH. The number of elements is computed as (bytes/bytesPerElement), wherebytesPerElementis determined from the data format and number of components set usingTexRefSetFormat.- Parameters:
ByteOffset- returned byte offsethTexRef- texture reference to binddptr- device pointer to bindbytes- size of memory to bind in bytes
-
ncuTexRefSetAddress2D
public static int ncuTexRefSetAddress2D(long hTexRef, long desc, long dptr, long Pitch) Unsafe version of:TexRefSetAddress2D -
cuTexRefSetAddress2D
public static int cuTexRefSetAddress2D(long hTexRef, CUDA_ARRAY_DESCRIPTOR desc, long dptr, long Pitch) Binds an address as a 2D texture reference. (Deprecated)Binds a linear address range to the texture reference
hTexRef. Any previous address or CUDA array state associated with the texture reference is superseded by this function. Any memory previously bound tohTexRefis unbound.Using a
tex2D()function inside a kernel requires a call to eitherTexRefSetArrayto bind the corresponding texture reference to an array, orTexRefSetAddress2Dto bind the texture reference to linear memory.Function calls to
TexRefSetFormatcannot follow calls toTexRefSetAddress2Dfor the same texture reference.It is required that
dptrbe aligned to the appropriate hardware-specific texture alignment. You can query this value using the device attributeDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT. If an unaligneddptris supplied,CUDA_ERROR_INVALID_VALUEis returned.Pitchhas to be aligned to the hardware-specific texture pitch alignment. This value can be queried using the device attributeDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT. If an unalignedPitchis supplied,CUDA_ERROR_INVALID_VALUEis returned.WidthandHeight, which are specified in elements (or texels), cannot exceedDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTHandDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHTrespectively.Pitch, which is specified in bytes, cannot exceedDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH.- Parameters:
hTexRef- texture reference to binddesc- descriptor of CUDA arraydptr- device pointer to bindPitch- line pitch in bytes
-
cuTexRefSetFormat
public static int cuTexRefSetFormat(long hTexRef, int fmt, int NumPackedComponents) Sets the format for a texture reference. (Deprecated)Specifies the format of the data to be read by the texture reference
hTexRef.fmtandNumPackedComponentsare exactly analogous to theFormatandNumChannelsmembers of theCUDA_ARRAY_DESCRIPTORstructure: They specify the format of each component and the number of components per array element.- Parameters:
hTexRef- texture referencefmt- format to setNumPackedComponents- number of components per array element
-
cuTexRefSetAddressMode
public static int cuTexRefSetAddressMode(long hTexRef, int dim, int am) Sets the addressing mode for a texture reference. (Deprecated)Specifies the addressing mode
amfor the given dimensiondimof the texture referencehTexRef. Ifdimis zero, the addressing mode is applied to the first parameter of the functions used to fetch from the texture; ifdimis 1, the second, and so on.Note that this call has no effect if
hTexRefis bound to linear memory. Also, if the flag,TRSF_NORMALIZED_COORDINATES, is not set, the only supported address mode isTR_ADDRESS_MODE_CLAMP.- Parameters:
hTexRef- texture referencedim- dimensionam- addressing mode to set
-
cuTexRefSetFilterMode
public static int cuTexRefSetFilterMode(long hTexRef, int fm) Sets the filtering mode for a texture reference. (Deprecated)Specifies the filtering mode
fmto be used when reading memory through the texture referencehTexRef.Note that this call has no effect if
hTexRefis bound to linear memory.- Parameters:
hTexRef- texture referencefm- filtering mode to set
-
cuTexRefSetMipmapFilterMode
public static int cuTexRefSetMipmapFilterMode(long hTexRef, int fm) Sets the mipmap filtering mode for a texture reference (Deprecated)Specifies the mipmap filtering mode
fmto be used when reading memory through the texture referencehTexRef.Note that this call has no effect if
hTexRefis not bound to a mipmapped array.- Parameters:
hTexRef- texture referencefm- filtering mode to set
-
cuTexRefSetMipmapLevelBias
public static int cuTexRefSetMipmapLevelBias(long hTexRef, float bias) Sets the mipmap level bias for a texture reference. (Deprecated)Specifies the mipmap level bias
biasto be added to the specified mipmap level when reading memory through the texture referencehTexRef.Note that this call has no effect if
hTexRefis not bound to a mipmapped array.- Parameters:
hTexRef- texture referencebias- mipmap level bias
-
cuTexRefSetMipmapLevelClamp
public static int cuTexRefSetMipmapLevelClamp(long hTexRef, float minMipmapLevelClamp, float maxMipmapLevelClamp) Sets the mipmap min/max mipmap level clamps for a texture reference. (Deprecated)Specifies the min/max mipmap level clamps,
minMipmapLevelClampandmaxMipmapLevelClamprespectively, to be used when reading memory through the texture referencehTexRef.Note that this call has no effect if
hTexRefis not bound to a mipmapped array.- Parameters:
hTexRef- texture referenceminMipmapLevelClamp- mipmap min level clampmaxMipmapLevelClamp- mipmap max level clamp
-
cuTexRefSetMaxAnisotropy
public static int cuTexRefSetMaxAnisotropy(long hTexRef, int maxAniso) Sets the maximum anisotropy for a texture reference. (Deprecated)Specifies the maximum anisotropy
maxAnisoto be used when reading memory through the texture referencehTexRef.Note that this call has no effect if
hTexRefis bound to linear memory.- Parameters:
hTexRef- texture referencemaxAniso- maximum anisotropy
-
ncuTexRefSetBorderColor
public static int ncuTexRefSetBorderColor(long hTexRef, long pBorderColor) Unsafe version of:TexRefSetBorderColor -
cuTexRefSetBorderColor
Sets the border color for a texture reference. (Deprecated)Specifies the value of the RGBA color via the
pBorderColorto the texture referencehTexRef. The color value supports only float type and holds color components in the following sequence:pBorderColor[0]holds 'R' componentpBorderColor[1]holds 'G' componentpBorderColor[2]holds 'B' componentpBorderColor[3]holds 'A' component.Note that the color values can be set only when the Address mode is set to
TR_ADDRESS_MODE_BORDERusingTexRefSetAddressMode. Applications using integer border color values have to "reinterpret_cast" their values to float.- Parameters:
hTexRef- texture referencepBorderColor- RGBA color
-
cuTexRefSetFlags
public static int cuTexRefSetFlags(long hTexRef, int Flags) Sets the flags for a texture reference. (Deprecated)Specifies optional flags via
Flagsto specify the behavior of data returned through the texture referencehTexRef. The valid flags are:TRSF_READ_AS_INTEGER, which suppresses the default behavior of having the texture promote integer data to floating point data in the range [0, 1]. Note that texture with 32-bit integer format would not be promoted, regardless of whether or not this flag is specified;TRSF_NORMALIZED_COORDINATES, which suppresses the default behavior of having the texture coordinates range from [0, Dim) where Dim is the width or height of the CUDA array. Instead, the texture coordinates [0, 1.0) reference the entire breadth of the array dimension;TRSF_DISABLE_TRILINEAR_OPTIMIZATION, which disables any trilinear filtering optimizations. Trilinear optimizations improve texture filtering performance by allowing bilinear filtering on textures in scenarios where it can closely approximate the expected results.
- Parameters:
hTexRef- texture referenceFlags- optional flags to set
-
ncuTexRefGetAddress
public static int ncuTexRefGetAddress(long pdptr, long hTexRef) Unsafe version of:TexRefGetAddress -
cuTexRefGetAddress
Gets the address associated with a texture reference. (Deprecated)Returns in
*pdptrthe base address bound to the texture referencehTexRef, or returnsCUDA_ERROR_INVALID_VALUEif the texture reference is not bound to any device memory range.- Parameters:
pdptr- returned device addresshTexRef- texture reference
-
ncuTexRefGetArray
public static int ncuTexRefGetArray(long phArray, long hTexRef) Unsafe version of:TexRefGetArray -
cuTexRefGetArray
Gets the array bound to a texture reference. (Deprecated)Returns in
*phArraythe CUDA array bound to the texture referencehTexRef, or returnsCUDA_ERROR_INVALID_VALUEif the texture reference is not bound to any CUDA array.- Parameters:
phArray- returned arrayhTexRef- texture reference
-
ncuTexRefGetMipmappedArray
public static int ncuTexRefGetMipmappedArray(long phMipmappedArray, long hTexRef) Unsafe version of:TexRefGetMipmappedArray -
cuTexRefGetMipmappedArray
Gets the mipmapped array bound to a texture reference. (Deprecated)Returns in
*phMipmappedArraythe CUDA mipmapped array bound to the texture referencehTexRef, or returnsCUDA_ERROR_INVALID_VALUEif the texture reference is not bound to any CUDA mipmapped array.- Parameters:
phMipmappedArray- returned mipmapped arrayhTexRef- texture reference
-
ncuTexRefGetAddressMode
public static int ncuTexRefGetAddressMode(long pam, long hTexRef, int dim) Unsafe version of:TexRefGetAddressMode -
cuTexRefGetAddressMode
Gets the addressing mode used by a texture reference. (Deprecated)Returns in
*pamthe addressing mode corresponding to the dimensiondimof the texture referencehTexRef. Currently, the only valid value fordimare 0 and 1.- Parameters:
pam- returned addressing modehTexRef- texture referencedim- dimension
-
ncuTexRefGetFilterMode
public static int ncuTexRefGetFilterMode(long pfm, long hTexRef) Unsafe version of:TexRefGetFilterMode -
cuTexRefGetFilterMode
Gets the filter-mode used by a texture reference. (Deprecated)Returns in
*pfmthe filtering mode of the texture referencehTexRef.- Parameters:
pfm- returned filtering modehTexRef- texture reference
-
ncuTexRefGetFormat
public static int ncuTexRefGetFormat(long pFormat, long pNumChannels, long hTexRef) Unsafe version of:TexRefGetFormat -
cuTexRefGetFormat
public static int cuTexRefGetFormat(IntBuffer pFormat, @Nullable IntBuffer pNumChannels, long hTexRef) Gets the format used by a texture reference. (Deprecated)Returns in
*pFormatand*pNumChannelsthe format and number of components of the CUDA array bound to the texture referencehTexRef. IfpFormatorpNumChannelsisNULL, it will be ignored.- Parameters:
pFormat- returned formatpNumChannels- returned number of componentshTexRef- texture reference
-
ncuTexRefGetMipmapFilterMode
public static int ncuTexRefGetMipmapFilterMode(long pfm, long hTexRef) Unsafe version of:TexRefGetMipmapFilterMode -
cuTexRefGetMipmapFilterMode
Gets the mipmap filtering mode for a texture reference. (Deprecated)Returns the mipmap filtering mode in
pfmthat's used when reading memory through the texture referencehTexRef.- Parameters:
pfm- returned mipmap filtering modehTexRef- texture reference
-
ncuTexRefGetMipmapLevelBias
public static int ncuTexRefGetMipmapLevelBias(long pbias, long hTexRef) Unsafe version of:TexRefGetMipmapLevelBias -
cuTexRefGetMipmapLevelBias
Gets the mipmap level bias for a texture reference. (Deprecated)Returns the mipmap level bias in
pBiasthat's added to the specified mipmap level when reading memory through the texture referencehTexRef.- Parameters:
pbias- returned mipmap level biashTexRef- texture reference
-
ncuTexRefGetMipmapLevelClamp
public static int ncuTexRefGetMipmapLevelClamp(long pminMipmapLevelClamp, long pmaxMipmapLevelClamp, long hTexRef) Unsafe version of:TexRefGetMipmapLevelClamp -
cuTexRefGetMipmapLevelClamp
public static int cuTexRefGetMipmapLevelClamp(FloatBuffer pminMipmapLevelClamp, FloatBuffer pmaxMipmapLevelClamp, long hTexRef) Gets the min/max mipmap level clamps for a texture reference. (Deprecated)Returns the min/max mipmap level clamps in
pminMipmapLevelClampandpmaxMipmapLevelClampthat's used when reading memory through the texture referencehTexRef.- Parameters:
pminMipmapLevelClamp- returned mipmap min level clamppmaxMipmapLevelClamp- returned mipmap max level clamphTexRef- texture reference
-
ncuTexRefGetMaxAnisotropy
public static int ncuTexRefGetMaxAnisotropy(long pmaxAniso, long hTexRef) Unsafe version of:TexRefGetMaxAnisotropy -
cuTexRefGetMaxAnisotropy
Gets the maximum anisotropy for a texture reference. (Deprecated)Returns the maximum anisotropy in
pmaxAnisothat's used when reading memory through the texture referencehTexRef.- Parameters:
pmaxAniso- returned maximum anisotropyhTexRef- texture reference
-
ncuTexRefGetBorderColor
public static int ncuTexRefGetBorderColor(long pBorderColor, long hTexRef) Unsafe version of:TexRefGetBorderColor -
cuTexRefGetBorderColor
Gets the border color used by a texture reference. (Deprecated)Returns in
pBorderColor, values of the RGBA color used by the texture referencehTexRef. The color value is of type float and holds color components in the following sequence: pBorderColor[0] holds 'R' component pBorderColor[1] holds 'G' component pBorderColor[2] holds 'B' component pBorderColor[3] holds 'A' component- Parameters:
pBorderColor- returned Type and Value of RGBA colorhTexRef- texture reference
-
ncuTexRefGetFlags
public static int ncuTexRefGetFlags(long pFlags, long hTexRef) Unsafe version of:TexRefGetFlags -
cuTexRefGetFlags
Gets the flags used by a texture reference. (Deprecated)Returns in
*pFlagsthe flags of the texture referencehTexRef.- Parameters:
pFlags- returned flagshTexRef- texture reference
-
ncuTexRefCreate
public static int ncuTexRefCreate(long pTexRef) Unsafe version of:TexRefCreate -
cuTexRefCreate
Creates a texture reference. (Deprecated)Creates a texture reference and returns its handle in
*pTexRef. Once created, the application must callTexRefSetArrayorTexRefSetAddressto associate the reference with allocated memory. Other texture reference functions are used to specify the format and interpretation (addressing, filtering, etc.) to be used when the memory is read through this texture reference.- Parameters:
pTexRef- returned texture reference
-
cuTexRefDestroy
public static int cuTexRefDestroy(long hTexRef) Destroys a texture reference. (Deprecated)Destroys the texture reference specified by
hTexRef.- Parameters:
hTexRef- texture reference to destroy
-
cuSurfRefSetArray
public static int cuSurfRefSetArray(long hSurfRef, long hArray, int Flags) Sets the CUDA array for a surface reference.Deprecated:Sets the CUDA array
hArrayto be read and written by the surface referencehSurfRef. Any previous CUDA array state associated with the surface reference is superseded by this function.Flagsmust be set to 0. TheCUDA_ARRAY3D_SURFACE_LDSTflag must have been set for the CUDA array. Any CUDA array previously bound tohSurfRefis unbound.- Parameters:
hSurfRef- surface reference handlehArray- CUDA array handleFlags- set to 0
-
ncuSurfRefGetArray
public static int ncuSurfRefGetArray(long phArray, long hSurfRef) Unsafe version of:SurfRefGetArray -
cuSurfRefGetArray
Passes back the CUDA array bound to a surface reference. (Deprecated)Returns in
*phArraythe CUDA array bound to the surface referencehSurfRef, or returnsCUDA_ERROR_INVALID_VALUEif the surface reference is not bound to any CUDA array.- Parameters:
phArray- surface reference handlehSurfRef- surface reference handle
-
ncuTexObjectCreate
public static int ncuTexObjectCreate(long pTexObject, long pResDesc, long pTexDesc, long pResViewDesc) Unsafe version of:TexObjectCreate -
cuTexObjectCreate
public static int cuTexObjectCreate(LongBuffer pTexObject, CUDA_RESOURCE_DESC pResDesc, CUDA_TEXTURE_DESC pTexDesc, CUDA_RESOURCE_VIEW_DESC pResViewDesc) Creates a texture object.Creates a texture object and returns it in
pTexObject.pResDescdescribes the data to texture from.pTexDescdescribes how the data should be sampled.pResViewDescis an optional argument that specifies an alternate format for the data described bypResDesc, and also describes the subresource region to restrict access to when texturing.pResViewDesccan only be specified if the type of resource is a CUDA array or a CUDA mipmapped array.Texture objects are only supported on devices of compute capability 3.0 or higher. Additionally, a texture object is an opaque value, and, as such, should only be accessed through CUDA API calls.
- If
CUDA_RESOURCE_DESC::resTypeis set toRESOURCE_TYPE_ARRAY,CUDA_RESOURCE_DESC::res::array::hArraymust be set to a valid CUDA array handle. - If
CUDA_RESOURCE_DESC::resTypeis set toRESOURCE_TYPE_MIPMAPPED_ARRAY,CUDA_RESOURCE_DESC::res::mipmap::hMipmappedArraymust be set to a valid CUDA mipmapped array handle. - If
CUDA_RESOURCE_DESC::resTypeis set toRESOURCE_TYPE_LINEAR,CUDA_RESOURCE_DESC::res::linear::devPtrmust be set to a valid device pointer, that is aligned toDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT.CUDA_RESOURCE_DESC::res::linear::formatandCUDA_RESOURCE_DESC::res::linear::numChannelsdescribe the format of each component and the number of components per array element.CUDA_RESOURCE_DESC::res::linear::sizeInBytesspecifies the size of the array in bytes. The total number of elements in the linear address range cannot exceedDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH. The number of elements is computed as(sizeInBytes / (sizeof(format) * numChannels)). - If
CUDA_RESOURCE_DESC::resTypeis set toRESOURCE_TYPE_PITCH2D,CUDA_RESOURCE_DESC::res::pitch2D::devPtrmust be set to a valid device pointer, that is aligned toDEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT.CUDA_RESOURCE_DESC::res::pitch2D::formatandCUDA_RESOURCE_DESC::res::pitch2D::numChannelsdescribe the format of each component and the number of components per array element.CUDA_RESOURCE_DESC::res::pitch2D::widthandCUDA_RESOURCE_DESC::res::pitch2D::heightspecify the width and height of the array in elements, and cannot exceedDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTHandDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHTrespectively.CUDA_RESOURCE_DESC::res::pitch2D::pitchInBytesspecifies the pitch between two rows in bytes and has to be aligned toDEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT. Pitch cannot exceedDEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH. flagsmust be set to zero.
CUDA_TEXTURE_DESC::addressModespecifies the addressing mode for each dimension of the texture data. This is ignored ifCUDA_RESOURCE_DESC::resTypeisRESOURCE_TYPE_LINEAR. Also, if the flag,TRSF_NORMALIZED_COORDINATESis not set, the only supported address mode isTR_ADDRESS_MODE_CLAMP.CUDA_TEXTURE_DESC::filterModespecifies the filtering mode to be used when fetching from the texture. This is ignored ifCUDA_RESOURCE_DESC::resTypeisRESOURCE_TYPE_LINEAR.CUDA_TEXTURE_DESC::flagscan be any combination of the following:TRSF_READ_AS_INTEGER, which suppresses the default behavior of having the texture promote integer data to floating point data in the range [0, 1]. Note that texture with 32-bit integer format would not be promoted, regardless of whether or not this flag is specified.TRSF_NORMALIZED_COORDINATES, which suppresses the default behavior of having the texture coordinates range from [0, Dim) where Dim is the width or height of the CUDA array. Instead, the texture coordinates [0, 1.0) reference the entire breadth of the array dimension; Note that for CUDA mipmapped arrays, this flag has to be set.TRSF_DISABLE_TRILINEAR_OPTIMIZATION, which disables any trilinear filtering optimizations. Trilinear optimizations improve texture filtering performance by allowing bilinear filtering on textures in scenarios where it can closely approximate the expected results.
CUDA_TEXTURE_DESC::maxAnisotropyspecifies the maximum anisotropy ratio to be used when doing anisotropic filtering. This value will be clamped to the range [1,16].CUDA_TEXTURE_DESC::mipmapFilterModespecifies the filter mode when the calculated mipmap level lies between two defined mipmap levels.CUDA_TEXTURE_DESC::mipmapLevelBiasspecifies the offset to be applied to the calculated mipmap level.CUDA_TEXTURE_DESC::minMipmapLevelClampspecifies the lower end of the mipmap level range to clamp access to.CUDA_TEXTURE_DESC::maxMipmapLevelClampspecifies the upper end of the mipmap level range to clamp access to.
CUDA_RESOURCE_VIEW_DESC::formatspecifies how the data contained in the CUDA array or CUDA mipmapped array should be interpreted. Note that this can incur a change in size of the texture data. If the resource view format is a block compressed format, then the underlying CUDA array or CUDA mipmapped array has to have a base of formatAD_FORMAT_UNSIGNED_INT32. with 2 or 4 channels, depending on the block compressed format. For ex., BC1 and BC4 require the underlying CUDA array to have a format ofAD_FORMAT_UNSIGNED_INT32with 2 channels. The other BC formats require the underlying resource to have the same base format but with 4 channels.CUDA_RESOURCE_VIEW_DESC::widthspecifies the new width of the texture data. If the resource view format is a block compressed format, this value has to be 4 times the original width of the resource. For non block compressed formats, this value has to be equal to that of the original resource.CUDA_RESOURCE_VIEW_DESC::heightspecifies the new height of the texture data. If the resource view format is a block compressed format, this value has to be 4 times the original height of the resource. For non block compressed formats, this value has to be equal to that of the original resource.CUDA_RESOURCE_VIEW_DESC::depthspecifies the new depth of the texture data. This value has to be equal to that of the original resource.CUDA_RESOURCE_VIEW_DESC::firstMipmapLevelspecifies the most detailed mipmap level. This will be the new mipmap level zero. For non-mipmapped resources, this value has to be zero.CUDA_TEXTURE_DESC::minMipmapLevelClampandCUDA_TEXTURE_DESC::maxMipmapLevelClampwill be relative to this value. For ex., if thefirstMipmapLevelis set to 2, and aminMipmapLevelClampof 1.2 is specified, then the actual minimum mipmap level clamp will be 3.2.CUDA_RESOURCE_VIEW_DESC::lastMipmapLevelspecifies the least detailed mipmap level. For non-mipmapped resources, this value has to be zero.CUDA_RESOURCE_VIEW_DESC::firstLayerspecifies the first layer index for layered textures. This will be the new layer zero. For non-layered resources, this value has to be zero.CUDA_RESOURCE_VIEW_DESC::lastLayerspecifies the last layer index for layered textures. For non-layered resources, this value has to be zero.
- Parameters:
pTexObject- texture object to createpResDesc- resource descriptorpTexDesc- texture descriptorpResViewDesc- resource view descriptor
- If
-
cuTexObjectDestroy
public static int cuTexObjectDestroy(long texObject) Destroys a texture object.Destroys the texture object specified by
texObject.- Parameters:
texObject- texture object to destroy
-
ncuTexObjectGetResourceDesc
public static int ncuTexObjectGetResourceDesc(long pResDesc, long texObject) Unsafe version of:TexObjectGetResourceDesc -
cuTexObjectGetResourceDesc
Returns a texture object's resource descriptor.Returns the resource descriptor for the texture object specified by
texObject.- Parameters:
pResDesc- resource descriptortexObject- texture object
-
ncuTexObjectGetTextureDesc
public static int ncuTexObjectGetTextureDesc(long pTexDesc, long texObject) Unsafe version of:TexObjectGetTextureDesc -
cuTexObjectGetTextureDesc
Returns a texture object's texture descriptor.Returns the texture descriptor for the texture object specified by
texObject.- Parameters:
pTexDesc- texture descriptortexObject- texture object
-
ncuTexObjectGetResourceViewDesc
public static int ncuTexObjectGetResourceViewDesc(long pResViewDesc, long texObject) Unsafe version of:TexObjectGetResourceViewDesc -
cuTexObjectGetResourceViewDesc
public static int cuTexObjectGetResourceViewDesc(CUDA_RESOURCE_VIEW_DESC pResViewDesc, long texObject) Returns a texture object's resource view descriptor.Returns the resource view descriptor for the texture object specified by
texObject. If no resource view was set fortexObject, theCUDA_ERROR_INVALID_VALUEis returned.- Parameters:
pResViewDesc- resource view descriptortexObject- texture object
-
ncuSurfObjectCreate
public static int ncuSurfObjectCreate(long pSurfObject, long pResDesc) Unsafe version of:SurfObjectCreate -
cuSurfObjectCreate
Creates a surface object.Creates a surface object and returns it in
pSurfObject.pResDescdescribes the data to perform surface load/stores on.CUDA_RESOURCE_DESC::resTypemust beRESOURCE_TYPE_ARRAYandCUDA_RESOURCE_DESC::res::array::hArraymust be set to a valid CUDA array handle.CUDA_RESOURCE_DESC::flagsmust be set to zero.Surface objects are only supported on devices of compute capability 3.0 or higher. Additionally, a surface object is an opaque value, and, as such, should only be accessed through CUDA API calls.
- Parameters:
pSurfObject- surface object to createpResDesc- resource descriptor
-
cuSurfObjectDestroy
public static int cuSurfObjectDestroy(long surfObject) Destroys a surface object.Destroys the surface object specified by
surfObject.- Parameters:
surfObject- surface object to destroy
-
ncuSurfObjectGetResourceDesc
public static int ncuSurfObjectGetResourceDesc(long pResDesc, long surfObject) Unsafe version of:SurfObjectGetResourceDesc -
cuSurfObjectGetResourceDesc
Returns a surface object's resource descriptor.Returns the resource descriptor for the surface object specified by
surfObject.- Parameters:
pResDesc- resource descriptorsurfObject- surface object
-
ncuDeviceCanAccessPeer
public static int ncuDeviceCanAccessPeer(long canAccessPeer, int dev, int peerDev) Unsafe version of:DeviceCanAccessPeer -
cuDeviceCanAccessPeer
Queries if a device may directly access a peer device's memory.Returns in
*canAccessPeera value of 1 if contexts ondevare capable of directly accessing memory from contexts onpeerDevand 0 otherwise. If direct access ofpeerDevfromdevis possible, then access may be enabled on two specific contexts by callingCtxEnablePeerAccess.- Parameters:
canAccessPeer- returned access capabilitydev- device from which allocations onpeerDevare to be directly accessedpeerDev- device on which the allocations to be directly accessed bydevreside
-
cuCtxEnablePeerAccess
public static int cuCtxEnablePeerAccess(long peerContext, int Flags) Enables direct access to memory allocations in a peer context.If both the current context and
peerContextare on devices which support unified addressing (as may be queried usingDEVICE_ATTRIBUTE_UNIFIED_ADDRESSING) and same major compute capability, then on success all allocations frompeerContextwill immediately be accessible by the current context. See ref for additional details.Note that access granted by this call is unidirectional and that in order to access memory from the current context in
peerContext, a separate symmetric call toCtxEnablePeerAccessis required.Note that there are both device-wide and system-wide limitations per system configuration, as noted in the CUDA Programming Guide under the section "Peer-to-Peer Memory Access".
Returns
CUDA_ERROR_PEER_ACCESS_UNSUPPORTEDifDeviceCanAccessPeerindicates that theCUdeviceof the current context cannot directly access memory from theCUdeviceofpeerContext.Returns
CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLEDif direct access ofpeerContextfrom the current context has already been enabled.Returns
CUDA_ERROR_TOO_MANY_PEERSif direct peer access is not possible because hardware resources required for peer access have been exhausted.Returns
CUDA_ERROR_INVALID_CONTEXTif there is no current context,peerContextis not a valid context, or if the current context ispeerContext.Returns
CUDA_ERROR_INVALID_VALUEifFlagsis not 0.- Parameters:
peerContext- peer context to enable direct access to from the current contextFlags- reserved for future use and must be set to 0
-
cuCtxDisablePeerAccess
public static int cuCtxDisablePeerAccess(long peerContext) Disables direct access to memory allocations in a peer context and unregisters any registered allocations.Returns
CUDA_ERROR_PEER_ACCESS_NOT_ENABLEDif direct peer access has not yet been enabled frompeerContextto the current context.Returns
CUDA_ERROR_INVALID_CONTEXTif there is no current context, or ifpeerContextis not a valid context.- Parameters:
peerContext- peer context to disable direct access to
-
ncuDeviceGetP2PAttribute
public static int ncuDeviceGetP2PAttribute(long value, int attrib, int srcDevice, int dstDevice) Unsafe version of:DeviceGetP2PAttribute -
cuDeviceGetP2PAttribute
public static int cuDeviceGetP2PAttribute(IntBuffer value, int attrib, int srcDevice, int dstDevice) Queries attributes of the link between two devices.Returns in
*valuethe value of the requested attributeattribof the link betweensrcDeviceanddstDevice. The supported attributes are:DEVICE_P2P_ATTRIBUTE_PERFORMANCE_RANK: A relative value indicating the performance of the link between two devices.DEVICE_P2P_ATTRIBUTE_ACCESS_SUPPORTEDP2P: 1 if P2P Access is enable.DEVICE_P2P_ATTRIBUTE_NATIVE_ATOMIC_SUPPORTED: 1 if Atomic operations over the link are supported.DEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTED: 1 if cudaArray can be accessed over the link.
Returns
CUDA_ERROR_INVALID_DEVICEifsrcDeviceordstDeviceare not valid or if they represent the same device.Returns
CUDA_ERROR_INVALID_VALUEifattribis not valid or ifvalueis a null pointer.- Parameters:
value- returned value of the requested attributeattrib- the requested attribute of the link betweensrcDeviceanddstDevicesrcDevice- the source device of the target linkdstDevice- the destination device of the target link
-
cuGraphicsUnregisterResource
public static int cuGraphicsUnregisterResource(long resource) Unregisters a graphics resource for access by CUDA.Unregisters the graphics resource
resourceso it is not accessible by CUDA unless registered again.If
resourceis invalid thenCUDA_ERROR_INVALID_HANDLEis returned.- Parameters:
resource- resource to unregister
-
ncuGraphicsSubResourceGetMappedArray
public static int ncuGraphicsSubResourceGetMappedArray(long pArray, long resource, int arrayIndex, int mipLevel) Unsafe version of:GraphicsSubResourceGetMappedArray -
cuGraphicsSubResourceGetMappedArray
public static int cuGraphicsSubResourceGetMappedArray(PointerBuffer pArray, long resource, int arrayIndex, int mipLevel) Get an array through which to access a subresource of a mapped graphics resource.Returns in
*pArrayan array through which the subresource of the mapped graphics resourceresourcewhich corresponds to array indexarrayIndexand mipmap levelmipLevelmay be accessed. The value set in*pArraymay change every time thatresourceis mapped.If
resourceis not a texture then it cannot be accessed via an array andCUDA_ERROR_NOT_MAPPED_AS_ARRAYis returned. IfarrayIndexis not a valid array index forresourcethenCUDA_ERROR_INVALID_VALUEis returned. IfmipLevelis not a valid mipmap level forresourcethenCUDA_ERROR_INVALID_VALUEis returned. Ifresourceis not mapped thenCUDA_ERROR_NOT_MAPPEDis returned.- Parameters:
pArray- returned array through which a subresource ofresourcemay be accessedresource- mapped resource to accessarrayIndex- array index for array textures or cubemap face index as defined byCUarray_cubemap_facefor cubemap textures for the subresource to accessmipLevel- mipmap level for the subresource to access
-
ncuGraphicsResourceGetMappedMipmappedArray
public static int ncuGraphicsResourceGetMappedMipmappedArray(long pMipmappedArray, long resource) Unsafe version of:GraphicsResourceGetMappedMipmappedArray -
cuGraphicsResourceGetMappedMipmappedArray
public static int cuGraphicsResourceGetMappedMipmappedArray(PointerBuffer pMipmappedArray, long resource) Get a mipmapped array through which to access a mapped graphics resource.Returns in
*pMipmappedArraya mipmapped array through which the mapped graphics resourceresource. The value set in*pMipmappedArraymay change every time thatresourceis mapped.If
resourceis not a texture then it cannot be accessed via a mipmapped array andCUDA_ERROR_NOT_MAPPED_AS_ARRAYis returned. Ifresourceis not mapped thenCUDA_ERROR_NOT_MAPPEDis returned.- Parameters:
pMipmappedArray- returned mipmapped array through whichresourcemay be accessedresource- mapped resource to access
-
ncuGraphicsResourceGetMappedPointer
public static int ncuGraphicsResourceGetMappedPointer(long pDevPtr, long pSize, long resource) Unsafe version of:GraphicsResourceGetMappedPointer -
cuGraphicsResourceGetMappedPointer
public static int cuGraphicsResourceGetMappedPointer(PointerBuffer pDevPtr, PointerBuffer pSize, long resource) Get a device pointer through which to access a mapped graphics resource.Returns in
*pDevPtra pointer through which the mapped graphics resourceresourcemay be accessed. Returns inpSizethe size of the memory in bytes which may be accessed from that pointer. The value set inpPointermay change every time thatresourceis mapped.If
resourceis not a buffer then it cannot be accessed via a pointer andCUDA_ERROR_NOT_MAPPED_AS_POINTERis returned. Ifresourceis not mapped thenCUDA_ERROR_NOT_MAPPEDis returned. *- Parameters:
pDevPtr- returned pointer through whichresourcemay be accessedpSize- returned size of the buffer accessible starting at*pPointerresource- mapped resource to access
-
cuGraphicsResourceSetMapFlags
public static int cuGraphicsResourceSetMapFlags(long resource, int flags) Set usage flags for mapping a graphics resource.Set
flagsfor mapping the graphics resourceresource.Changes to
flagswill take effect the next timeresourceis mapped. Theflagsargument may be any of the following:GRAPHICS_MAP_RESOURCE_FLAGS_NONE: Specifies no hints about how this resource will be used. It is therefore assumed that this resource will be read from and written to by CUDA kernels. This is the default value.GRAPHICS_MAP_RESOURCE_FLAGS_READ_ONLY: Specifies that CUDA kernels which access this resource will not write to this resource.GRAPHICS_MAP_RESOURCE_FLAGS_WRITE_DISCARD: Specifies that CUDA kernels which access this resource will not read from this resource and will write over the entire contents of the resource, so none of the data previously stored in the resource will be preserved.
If
resourceis presently mapped for access by CUDA thenCUDA_ERROR_ALREADY_MAPPEDis returned. Ifflagsis not one of the above values thenCUDA_ERROR_INVALID_VALUEis returned.- Parameters:
resource- registered resource to set flags forflags- parameters for resource mapping
-
ncuGraphicsMapResources
public static int ncuGraphicsMapResources(int count, long resources, long hStream) Unsafe version of:GraphicsMapResources- Parameters:
count- number of resources to map
-
cuGraphicsMapResources
Map graphics resources for access by CUDA.Maps the
countgraphics resources inresourcesfor access by CUDA.The resources in
resourcesmay be accessed by CUDA until they are unmapped. The graphics API from whichresourceswere registered should not access any resources while they are mapped by CUDA. If an application does so, the results are undefined.This function provides the synchronization guarantee that any graphics calls issued before
GraphicsMapResourceswill complete before any subsequent CUDA work issued instreambegins.If
resourcesincludes any duplicate entries thenCUDA_ERROR_INVALID_HANDLEis returned. If any ofresourcesare presently mapped for access by CUDA thenCUDA_ERROR_ALREADY_MAPPEDis returned.- Parameters:
resources- resources to map for CUDA usagehStream- stream with which to synchronize
-
ncuGraphicsUnmapResources
public static int ncuGraphicsUnmapResources(int count, long resources, long hStream) Unsafe version of:GraphicsUnmapResources- Parameters:
count- number of resources to unmap
-
cuGraphicsUnmapResources
Unmap graphics resources.Unmaps the
countgraphics resources inresources.Once unmapped, the resources in
resourcesmay not be accessed by CUDA until they are mapped again.This function provides the synchronization guarantee that any CUDA work issued in
streambeforeGraphicsUnmapResourceswill complete before any subsequently issued graphics work begins.If
resourcesincludes any duplicate entries thenCUDA_ERROR_INVALID_HANDLEis returned. If any ofresourcesare not presently mapped for access by CUDA thenCUDA_ERROR_NOT_MAPPEDis returned.- Parameters:
resources- resources to unmaphStream- stream with which to synchronize
-
ncuGetProcAddress
public static int ncuGetProcAddress(long symbol, long pfn, int cudaVersion, long flags) Unsafe version of:GetProcAddress -
cuGetProcAddress
public static int cuGetProcAddress(ByteBuffer symbol, PointerBuffer pfn, int cudaVersion, long flags) Returns the requested driver API function pointer.Returns in
**pfnthe address of the CUDA driver function for the requested CUDA version and flags.The CUDA version is specified as (1000 * major + 10 * minor), so CUDA 11.2 should be specified as 11020. For a requested driver symbol, if the specified CUDA version is greater than or equal to the CUDA version in which the driver symbol was introduced, this API will return the function pointer to the corresponding versioned function.
The pointer returned by the API should be cast to a function pointer matching the requested driver function's definition in the API header file. The function pointer typedef can be picked up from the corresponding typedefs header file. For example, cudaTypedefs.h consists of function pointer typedefs for driver APIs defined in cuda.h.
The API will return
CUDA_ERROR_NOT_FOUNDif the requested driver function is not supported on the platform, no ABI compatible driver function exists for the specifiedcudaVersionor if the driver symbol is invalid.The requested flags can be:
GET_PROC_ADDRESS_DEFAULT: This is the default mode. This is equivalent toGET_PROC_ADDRESS_PER_THREAD_DEFAULT_STREAMif the code is compiled with --default-stream per-thread compilation flag or the macroCUDA_API_PER_THREAD_DEFAULT_STREAMis defined;GET_PROC_ADDRESS_LEGACY_STREAMotherwise.GET_PROC_ADDRESS_LEGACY_STREAM: This will enable the search for all driver symbols that match the requested driver symbol name except the corresponding per-thread versions.GET_PROC_ADDRESS_PER_THREAD_DEFAULT_STREAM: This will enable the search for all driver symbols that match the requested driver symbol name including the per-thread versions. If a per-thread version is not found, the API will return the legacy version of the driver function.
- Parameters:
symbol- the base name of the driver API function to look for. As an example, for the driver APIcuMemAlloc_v2(),symbolwould becuMemAllocandcudaVersionwould be the ABI compatible CUDA version for the_v2variant.pfn- location to return the function pointer to the requested driver functioncudaVersion- the CUDA version to look for the requested driver symbolflags- flags to specify search options
-
cuGetProcAddress
public static int cuGetProcAddress(CharSequence symbol, PointerBuffer pfn, int cudaVersion, long flags) Returns the requested driver API function pointer.Returns in
**pfnthe address of the CUDA driver function for the requested CUDA version and flags.The CUDA version is specified as (1000 * major + 10 * minor), so CUDA 11.2 should be specified as 11020. For a requested driver symbol, if the specified CUDA version is greater than or equal to the CUDA version in which the driver symbol was introduced, this API will return the function pointer to the corresponding versioned function.
The pointer returned by the API should be cast to a function pointer matching the requested driver function's definition in the API header file. The function pointer typedef can be picked up from the corresponding typedefs header file. For example, cudaTypedefs.h consists of function pointer typedefs for driver APIs defined in cuda.h.
The API will return
CUDA_ERROR_NOT_FOUNDif the requested driver function is not supported on the platform, no ABI compatible driver function exists for the specifiedcudaVersionor if the driver symbol is invalid.The requested flags can be:
GET_PROC_ADDRESS_DEFAULT: This is the default mode. This is equivalent toGET_PROC_ADDRESS_PER_THREAD_DEFAULT_STREAMif the code is compiled with --default-stream per-thread compilation flag or the macroCUDA_API_PER_THREAD_DEFAULT_STREAMis defined;GET_PROC_ADDRESS_LEGACY_STREAMotherwise.GET_PROC_ADDRESS_LEGACY_STREAM: This will enable the search for all driver symbols that match the requested driver symbol name except the corresponding per-thread versions.GET_PROC_ADDRESS_PER_THREAD_DEFAULT_STREAM: This will enable the search for all driver symbols that match the requested driver symbol name including the per-thread versions. If a per-thread version is not found, the API will return the legacy version of the driver function.
- Parameters:
symbol- the base name of the driver API function to look for. As an example, for the driver APIcuMemAlloc_v2(),symbolwould becuMemAllocandcudaVersionwould be the ABI compatible CUDA version for the_v2variant.pfn- location to return the function pointer to the requested driver functioncudaVersion- the CUDA version to look for the requested driver symbolflags- flags to specify search options
-
ncuGetExportTable
public static int ncuGetExportTable(long ppExportTable, long pExportTableId) -
cuGetExportTable
-